Image denoising using deep CNN with batch renormalization
Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very difficult to train a deeper CNN for denoising tasks, and (2) most of deeper CNNs suffer from performance saturation. In this paper, we report the...
Saved in:
| Published in | Neural networks Vol. 121; pp. 461 - 473 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Ltd
01.01.2020
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very difficult to train a deeper CNN for denoising tasks, and (2) most of deeper CNNs suffer from performance saturation. In this paper, we report the design of a novel network called a batch-renormalization denoising network (BRDNet). Specifically, we combine two networks to increase the width of the network, and thus obtain more features. Because batch renormalization is fused into BRDNet, we can address the internal covariate shift and small mini-batch problems. Residual learning is also adopted in a holistic way to facilitate the network training. Dilated convolutions are exploited to extract more information for denoising tasks. Extensive experimental results show that BRDNet outperforms state-of-the-art image-denoising methods. The code of BRDNet is accessible at http://www.yongxu.org/lunwen.html. |
|---|---|
| AbstractList | Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very difficult to train a deeper CNN for denoising tasks, and (2) most of deeper CNNs suffer from performance saturation. In this paper, we report the design of a novel network called a batch-renormalization denoising network (BRDNet). Specifically, we combine two networks to increase the width of the network, and thus obtain more features. Because batch renormalization is fused into BRDNet, we can address the internal covariate shift and small mini-batch problems. Residual learning is also adopted in a holistic way to facilitate the network training. Dilated convolutions are exploited to extract more information for denoising tasks. Extensive experimental results show that BRDNet outperforms state-of-the-art image-denoising methods. The code of BRDNet is accessible at http://www.yongxu.org/lunwen.html. Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very difficult to train a deeper CNN for denoising tasks, and (2) most of deeper CNNs suffer from performance saturation. In this paper, we report the design of a novel network called a batch-renormalization denoising network (BRDNet). Specifically, we combine two networks to increase the width of the network, and thus obtain more features. Because batch renormalization is fused into BRDNet, we can address the internal covariate shift and small mini-batch problems. Residual learning is also adopted in a holistic way to facilitate the network training. Dilated convolutions are exploited to extract more information for denoising tasks. Extensive experimental results show that BRDNet outperforms state-of-the-art image-denoising methods. The code of BRDNet is accessible at http://www.yongxu.org/lunwen.html.Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very difficult to train a deeper CNN for denoising tasks, and (2) most of deeper CNNs suffer from performance saturation. In this paper, we report the design of a novel network called a batch-renormalization denoising network (BRDNet). Specifically, we combine two networks to increase the width of the network, and thus obtain more features. Because batch renormalization is fused into BRDNet, we can address the internal covariate shift and small mini-batch problems. Residual learning is also adopted in a holistic way to facilitate the network training. Dilated convolutions are exploited to extract more information for denoising tasks. Extensive experimental results show that BRDNet outperforms state-of-the-art image-denoising methods. The code of BRDNet is accessible at http://www.yongxu.org/lunwen.html. |
| Author | Xu, Yong Zuo, Wangmeng Tian, Chunwei |
| Author_xml | – sequence: 1 givenname: Chunwei surname: Tian fullname: Tian, Chunwei email: chunweitian@163.com organization: Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen, Shenzhen, 518055, Guangdong, China – sequence: 2 givenname: Yong surname: Xu fullname: Xu, Yong email: yongxu@ymail.com organization: Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen, Shenzhen, 518055, Guangdong, China – sequence: 3 givenname: Wangmeng surname: Zuo fullname: Zuo, Wangmeng email: wmzuo@hit.edu.cn organization: School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31629201$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkD1PwzAQhi1URMvHP0AoI0vC2Y4ShwEJVXxJVVnYLce-gKvEKbYDgl9PaIGBAZa75Xlf3T37ZOJ6h4QcU8go0OJslTkcHMaMAa0yEBkwtkNmVJRVykrBJmQGouJpAQKmZD-EFQAUIud7ZMppwaoxNyPVXaceMTHoehuse0yGzTSI62S-XCavNj4ltYr6KfEj4zvV2ncVbe8OyW6j2oBHX_uAPFxfPcxv08X9zd38cpFqXrCYGqNRKNWgVjWvtCoFV5RpzEsBBgXkeW2aQnFd1UDHo-rGcF4xbkpWF0zzA3K6rV37_nnAEGVng8a2VQ77IUjGoaR5zhkb0ZMvdKg7NHLtbaf8m_z-dgTyLaB9H4LH5gehID-lypXcSpWfUiUICZve818xbePGQfTKtv-FL7ZhHB29WPQyaItOo7EedZSmt38XfAADHpT3 |
| CitedBy_id | crossref_primary_10_1016_j_neunet_2020_06_010 crossref_primary_10_3390_app12126227 crossref_primary_10_1049_ipr2_13264 crossref_primary_10_1016_j_micron_2024_103615 crossref_primary_10_1142_S0219467825500093 crossref_primary_10_1109_ACCESS_2022_3160711 crossref_primary_10_3390_electronics11213535 crossref_primary_10_1007_s11071_022_07571_8 crossref_primary_10_1016_j_autcon_2021_103883 crossref_primary_10_1016_j_eswa_2023_120628 crossref_primary_10_1111_jfpe_14117 crossref_primary_10_1093_bib_bbab248 crossref_primary_10_1016_j_eswa_2022_118705 crossref_primary_10_1016_j_jvcir_2020_103015 crossref_primary_10_1007_s11042_024_18418_2 crossref_primary_10_1016_j_neunet_2023_12_003 crossref_primary_10_1109_TMM_2023_3240880 crossref_primary_10_1016_j_nima_2023_168505 crossref_primary_10_1109_TII_2023_3316184 crossref_primary_10_1007_s11554_020_01060_0 crossref_primary_10_1049_ipr2_13156 crossref_primary_10_1016_j_dsp_2023_104332 crossref_primary_10_1016_j_cviu_2023_103725 crossref_primary_10_2139_ssrn_4473320 crossref_primary_10_1016_j_neunet_2022_06_009 crossref_primary_10_3390_rs15020445 crossref_primary_10_1007_s00530_022_01035_0 crossref_primary_10_1016_j_dsp_2024_104835 crossref_primary_10_1109_TGRS_2024_3432601 crossref_primary_10_1515_bmt_2022_0180 crossref_primary_10_51354_mjen_852312 crossref_primary_10_1093_bib_bbab001 crossref_primary_10_1007_s11633_023_1466_0 crossref_primary_10_1007_s00371_021_02271_7 crossref_primary_10_7717_peerj_cs_1817 crossref_primary_10_1109_LGRS_2022_3145992 crossref_primary_10_1007_s11042_020_09018_x crossref_primary_10_1016_j_jclepro_2021_130101 crossref_primary_10_3788_IRLA20210957 crossref_primary_10_1016_j_dsp_2020_102898 crossref_primary_10_1016_j_eswa_2021_116016 crossref_primary_10_1109_TCSVT_2020_2997856 crossref_primary_10_1007_s11760_023_02674_0 crossref_primary_10_1093_mnras_stac281 crossref_primary_10_1142_S0219467824500578 crossref_primary_10_2139_ssrn_4185499 crossref_primary_10_1109_TCSVT_2022_3190516 crossref_primary_10_1109_TMM_2020_2999182 crossref_primary_10_1016_j_patrec_2024_01_006 crossref_primary_10_1142_S0218126625500690 crossref_primary_10_4018_IJITSA_321456 crossref_primary_10_1007_s11263_021_01466_8 crossref_primary_10_1186_s13634_021_00800_z crossref_primary_10_1007_s11063_022_10934_2 crossref_primary_10_3934_mbe_2020182 crossref_primary_10_1007_s10489_024_05394_1 crossref_primary_10_1109_TIP_2020_2980116 crossref_primary_10_3389_fpls_2023_1154176 crossref_primary_10_3389_fgene_2024_1349546 crossref_primary_10_1016_j_inffus_2022_12_015 crossref_primary_10_1109_ACCESS_2020_2999750 crossref_primary_10_1109_TII_2020_3024187 crossref_primary_10_1088_1742_6596_2216_1_012071 crossref_primary_10_3233_JIFS_232371 crossref_primary_10_1109_TSMC_2024_3429345 crossref_primary_10_1016_j_iswa_2023_200211 crossref_primary_10_1142_S0219467821500030 crossref_primary_10_1016_j_inffus_2023_102043 crossref_primary_10_1109_TMM_2024_3407656 crossref_primary_10_1007_s10723_022_09601_6 crossref_primary_10_1016_j_matpr_2021_01_790 crossref_primary_10_1111_1365_2478_13355 crossref_primary_10_1016_j_compbiomed_2023_107515 crossref_primary_10_3847_1538_4365_ad5c66 crossref_primary_10_1007_s11042_023_16209_9 crossref_primary_10_3390_rs14246300 crossref_primary_10_3390_electronics14020353 crossref_primary_10_1088_1361_6560_ad7e78 crossref_primary_10_1016_j_inffus_2022_03_006 crossref_primary_10_1007_s00034_023_02349_8 crossref_primary_10_11834_jig_211020 crossref_primary_10_1016_j_knosys_2023_111320 crossref_primary_10_1109_TMM_2020_3008028 crossref_primary_10_3390_electronics13010194 crossref_primary_10_1007_s00521_021_05920_z crossref_primary_10_1007_s12530_022_09419_3 crossref_primary_10_1016_j_engappai_2024_109558 crossref_primary_10_1016_j_knosys_2020_106235 crossref_primary_10_3847_1538_4357_acbfb4 crossref_primary_10_1109_TNNLS_2020_3048031 crossref_primary_10_1016_j_neunet_2020_07_025 crossref_primary_10_1016_j_neunet_2024_106218 crossref_primary_10_1007_s00521_020_05349_w crossref_primary_10_1016_j_jvcir_2020_102882 crossref_primary_10_1016_j_imavis_2024_105194 crossref_primary_10_1371_journal_pone_0254051 crossref_primary_10_1109_TCSVT_2023_3249796 crossref_primary_10_1016_j_neunet_2019_12_024 crossref_primary_10_1016_j_patcog_2024_110291 crossref_primary_10_1109_ACCESS_2019_2960578 crossref_primary_10_1007_s00530_021_00838_x crossref_primary_10_1109_TSP_2025_3534177 crossref_primary_10_1109_TGRS_2020_3034752 crossref_primary_10_1007_s11227_024_06646_0 crossref_primary_10_1016_j_neunet_2023_08_056 crossref_primary_10_3390_electronics11050757 crossref_primary_10_1016_j_neucom_2019_12_020 crossref_primary_10_1109_TGRS_2025_3534199 crossref_primary_10_1155_2021_5541134 crossref_primary_10_1007_s10044_022_01064_5 crossref_primary_10_1016_j_dsp_2022_103702 crossref_primary_10_3390_app14167044 crossref_primary_10_1016_j_phycom_2024_102577 crossref_primary_10_1007_s00521_024_09440_4 crossref_primary_10_1016_j_sigpro_2025_109886 crossref_primary_10_1016_j_imavis_2023_104709 crossref_primary_10_1038_s41598_023_38335_y crossref_primary_10_1080_01431161_2022_2066961 crossref_primary_10_1109_TMM_2024_3358962 crossref_primary_10_1109_TSP_2022_3154969 crossref_primary_10_1016_j_neunet_2020_07_035 crossref_primary_10_1109_TNNLS_2023_3274290 crossref_primary_10_1007_s11517_022_02731_9 crossref_primary_10_1016_j_engappai_2025_110275 crossref_primary_10_1007_s00530_024_01469_8 crossref_primary_10_1007_s11042_023_16346_1 crossref_primary_10_1016_j_procs_2024_04_204 crossref_primary_10_1016_j_compbiomed_2022_106385 crossref_primary_10_1016_j_neucom_2024_129044 crossref_primary_10_1049_ipr2_12536 crossref_primary_10_1109_ACCESS_2021_3084951 crossref_primary_10_3390_s21051810 crossref_primary_10_1109_JSEN_2021_3088840 crossref_primary_10_1088_1361_6501_ac4a19 crossref_primary_10_1007_s10845_023_02152_x crossref_primary_10_1007_s11063_023_11359_1 crossref_primary_10_1007_s11042_023_14334_z crossref_primary_10_1109_TSMC_2021_3069265 crossref_primary_10_1109_ACCESS_2020_3003375 crossref_primary_10_1038_s41524_023_01011_w crossref_primary_10_1016_j_image_2023_117077 crossref_primary_10_1007_s11042_023_16336_3 crossref_primary_10_1016_j_bspc_2020_102396 crossref_primary_10_1109_TCYB_2022_3170472 crossref_primary_10_1111_coin_70005 crossref_primary_10_1016_j_ijleo_2022_169089 crossref_primary_10_1080_13682199_2023_2229040 crossref_primary_10_3390_s23187713 crossref_primary_10_1109_ACCESS_2022_3222826 crossref_primary_10_1109_ACCESS_2021_3092425 crossref_primary_10_3390_app132011560 crossref_primary_10_1109_TMM_2021_3094058 crossref_primary_10_1016_j_neunet_2025_107270 crossref_primary_10_1016_j_neunet_2020_12_014 crossref_primary_10_1109_TPAMI_2024_3432812 crossref_primary_10_1007_s11760_024_03093_5 crossref_primary_10_1016_j_knosys_2023_111116 crossref_primary_10_3390_electronics13061075 crossref_primary_10_3390_s23125607 crossref_primary_10_1007_s10044_024_01313_9 crossref_primary_10_1109_ACCESS_2022_3162608 crossref_primary_10_1016_j_bspc_2021_102463 crossref_primary_10_3390_e25081176 crossref_primary_10_1016_j_inffus_2020_08_020 crossref_primary_10_1109_JSTARS_2021_3086139 crossref_primary_10_47836_pjst_30_1_01 crossref_primary_10_25046_aj050482 crossref_primary_10_1007_s00521_020_05313_8 crossref_primary_10_1038_s41598_021_95480_y crossref_primary_10_1016_j_ins_2023_119247 crossref_primary_10_1016_j_patcog_2024_111223 crossref_primary_10_1109_TCSVT_2020_3007723 crossref_primary_10_1002_nbm_5268 crossref_primary_10_1109_ACCESS_2020_2964271 crossref_primary_10_7717_peerj_cs_873 crossref_primary_10_1016_j_inffus_2021_07_001 crossref_primary_10_1109_TRS_2025_3527209 crossref_primary_10_1016_j_compbiomed_2022_105424 crossref_primary_10_1016_j_knosys_2021_106949 crossref_primary_10_1109_TSMC_2023_3289873 crossref_primary_10_3788_AI_2024_20001 crossref_primary_10_5909_JBE_2023_28_4_410 crossref_primary_10_1155_2023_6660715 crossref_primary_10_1049_bme2_5576927 crossref_primary_10_48175_IJARSCT_8524 crossref_primary_10_1016_j_neucom_2021_04_114 crossref_primary_10_3390_s21217024 crossref_primary_10_1007_s10278_024_01254_z crossref_primary_10_1016_j_neunet_2024_106378 crossref_primary_10_1088_1361_6560_ad8c93 crossref_primary_10_1109_TMM_2021_3079697 crossref_primary_10_1049_cit2_12110 crossref_primary_10_1016_j_isatra_2021_11_028 crossref_primary_10_1109_TMM_2020_3013408 crossref_primary_10_3390_s23041764 crossref_primary_10_1016_j_dsp_2023_104052 crossref_primary_10_1109_TIP_2020_2994443 crossref_primary_10_1016_j_imu_2020_100335 crossref_primary_10_1109_ACCESS_2020_2997072 crossref_primary_10_32604_cmc_2023_041195 crossref_primary_10_2139_ssrn_4189339 crossref_primary_10_1109_ACCESS_2020_2976826 crossref_primary_10_1007_s10044_024_01346_0 crossref_primary_10_1109_ACCESS_2020_3011989 crossref_primary_10_1007_s11042_022_12565_0 crossref_primary_10_15407_jai2022_01_288 crossref_primary_10_1109_ACCESS_2022_3169131 crossref_primary_10_12677_csa_2025_152043 crossref_primary_10_1007_s11042_022_12406_0 crossref_primary_10_1155_2020_8964321 crossref_primary_10_32604_cmc_2023_033111 crossref_primary_10_1016_j_neunet_2023_06_036 crossref_primary_10_1007_s12204_022_2453_2 crossref_primary_10_1007_s00138_024_01573_9 crossref_primary_10_1109_ACCESS_2022_3170490 crossref_primary_10_1109_TIV_2023_3327501 crossref_primary_10_1016_j_compeleceng_2024_109976 crossref_primary_10_1016_j_knosys_2025_113159 crossref_primary_10_3390_jmse10101383 crossref_primary_10_1109_ACCESS_2023_3264604 crossref_primary_10_1007_s00034_024_02892_y crossref_primary_10_1007_s00034_021_01883_7 crossref_primary_10_1016_j_ins_2020_06_032 crossref_primary_10_1016_j_neucom_2024_127473 crossref_primary_10_1109_TIP_2024_3456583 crossref_primary_10_1088_1742_6596_1854_1_012040 crossref_primary_10_1088_1755_1315_905_1_012059 crossref_primary_10_1109_TMM_2022_3179926 crossref_primary_10_1016_j_image_2022_116848 crossref_primary_10_1109_TNNLS_2022_3231917 crossref_primary_10_1016_j_engappai_2023_106755 crossref_primary_10_1016_j_jestch_2021_06_010 crossref_primary_10_1109_JLT_2024_3366294 crossref_primary_10_1109_TNNLS_2020_3016321 crossref_primary_10_1016_j_compscitech_2025_111050 crossref_primary_10_1007_s11063_021_10501_1 crossref_primary_10_1364_AO_419871 crossref_primary_10_1371_journal_pone_0274308 crossref_primary_10_48175_IJARSCT_4873 crossref_primary_10_3934_era_2025055 crossref_primary_10_1109_ACCESS_2023_3239835 crossref_primary_10_1016_j_eswa_2023_121666 crossref_primary_10_1007_s11517_024_03111_1 crossref_primary_10_1080_17538947_2024_2407519 crossref_primary_10_1109_TFUZZ_2024_3362792 crossref_primary_10_1016_j_engappai_2025_110017 crossref_primary_10_1007_s11063_023_11286_1 crossref_primary_10_1016_j_patcog_2023_110176 crossref_primary_10_3390_electronics13234613 crossref_primary_10_1080_0954898X_2024_2358950 crossref_primary_10_1049_ipr2_12499 crossref_primary_10_1109_TFUZZ_2023_3287734 crossref_primary_10_1007_s12065_021_00627_5 crossref_primary_10_1080_13682199_2023_2198350 crossref_primary_10_1109_ACCESS_2020_3040939 crossref_primary_10_7240_jeps_938188 crossref_primary_10_1109_ACCESS_2020_3006346 crossref_primary_10_1190_geo2021_0459_1 crossref_primary_10_7717_peerj_cs_2449 crossref_primary_10_1007_s10489_023_04660_y crossref_primary_10_3390_s23031486 crossref_primary_10_1016_j_asoc_2020_106884 crossref_primary_10_3390_technologies11040111 crossref_primary_10_1007_s00530_022_00960_4 crossref_primary_10_1007_s13721_022_00379_x crossref_primary_10_1111_exsy_13102 crossref_primary_10_1371_journal_pcbi_1012192 crossref_primary_10_1007_s10489_022_03717_8 crossref_primary_10_1371_journal_pone_0254586 crossref_primary_10_1109_JSEN_2024_3403856 crossref_primary_10_1016_j_camwa_2021_03_029 crossref_primary_10_1038_s41598_024_74777_8 crossref_primary_10_1016_j_knosys_2020_105526 crossref_primary_10_1140_epjp_s13360_021_01693_5 crossref_primary_10_1049_ipr2_12138 crossref_primary_10_1109_ACCESS_2021_3059477 crossref_primary_10_1049_ipr2_12394 crossref_primary_10_1088_1361_6560_ad6ede crossref_primary_10_3390_s25020317 crossref_primary_10_1007_s11042_021_11162_x crossref_primary_10_7717_peerj_cs_970 crossref_primary_10_1155_2020_4303725 crossref_primary_10_1016_j_infrared_2023_104761 crossref_primary_10_1007_s00371_021_02281_5 crossref_primary_10_1016_j_compeleceng_2024_109814 crossref_primary_10_3390_app13010028 crossref_primary_10_1007_s11063_023_11235_y crossref_primary_10_3788_AOS231120 crossref_primary_10_1007_s11042_022_13096_4 crossref_primary_10_1186_s13640_023_00617_w crossref_primary_10_1016_j_neunet_2020_10_014 crossref_primary_10_1016_j_patcog_2023_109603 crossref_primary_10_1109_ACCESS_2021_3091971 crossref_primary_10_1109_TCYB_2020_3043520 crossref_primary_10_1007_s00521_023_09314_1 crossref_primary_10_3390_s23135915 crossref_primary_10_1088_1755_1315_924_1_012022 crossref_primary_10_1016_j_inffus_2025_103013 crossref_primary_10_1109_TII_2022_3165869 crossref_primary_10_1109_TCSVT_2024_3429557 crossref_primary_10_1007_s11042_021_10754_x crossref_primary_10_1088_1755_1315_924_1_012009 crossref_primary_10_1016_j_patcog_2024_110563 crossref_primary_10_1364_AO_461967 crossref_primary_10_1016_j_jvcir_2023_103994 crossref_primary_10_1016_j_knosys_2020_105554 crossref_primary_10_1007_s00530_024_01284_1 crossref_primary_10_1109_TCSVT_2024_3402095 crossref_primary_10_1007_s00371_022_02749_y crossref_primary_10_14801_jkiit_2021_19_9_1 crossref_primary_10_1109_TDSC_2022_3140899 crossref_primary_10_1142_S0219467820500369 crossref_primary_10_1016_j_image_2025_117286 crossref_primary_10_3390_electronics11203375 crossref_primary_10_1016_j_dsp_2022_103407 crossref_primary_10_1016_j_dsp_2022_103528 crossref_primary_10_1007_s11760_021_01969_4 crossref_primary_10_1109_LSP_2021_3057544 crossref_primary_10_1007_s10462_021_09977_z |
| Cites_doi | 10.1109/ICCV.2015.123 10.1109/TIP.2012.2235847 10.1109/MSP.2017.2717489 10.1016/j.neunet.2018.02.002 10.1109/ICCV.2015.50 10.1109/TIP.2007.901238 10.1109/TIP.2009.2028254 10.1109/CVPR.2016.181 10.1109/TIP.2017.2662206 10.5201/ipol.2015.125 10.1109/LSP.2018.2829766 10.1016/0167-2789(92)90242-F 10.1109/TIP.2016.2631888 10.1016/j.trit.2017.03.001 10.1109/TCYB.2016.2536638 10.1109/CVPR.2014.366 10.1109/CVPR.2016.90 10.1007/s11263-008-0197-6 10.1109/TIP.2014.2316423 10.1109/83.563320 10.1109/TPAMI.2015.2439281 10.1109/TIP.2018.2811546 10.1109/TGRS.2019.2903875 10.1109/CVPR.2014.349 10.14419/ijet.v7i2.3.9964 10.1109/TIP.2018.2855433 10.1109/CVPR.2018.00262 10.1109/TIP.2015.2439041 10.1109/CVPR.2016.186 10.1109/CVPR.2015.7298594 10.1109/TBME.2012.2217493 10.1109/TPAMI.2016.2596743 10.1109/CVPR.2015.7298965 10.1016/j.neunet.2018.08.007 10.1109/TIP.2009.2028250 10.1109/CVPR.2018.00333 10.1109/CVPR.2017.294 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier Ltd Copyright © 2019 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2019 Elsevier Ltd – notice: Copyright © 2019 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.neunet.2019.08.022 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 473 |
| ExternalDocumentID | 31629201 10_1016_j_neunet_2019_08_022 S0893608019302394 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH CGR CUY CVF ECM EIF NPM PKN 7X8 |
| ID | FETCH-LOGICAL-c362t-ddce8aafecab39ca783a12ce4780de8044bdf6a3c9b01292bfd33923d72b62c3 |
| IEDL.DBID | .~1 |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Fri Jul 11 11:22:08 EDT 2025 Wed Feb 19 02:30:51 EST 2025 Thu Apr 24 22:52:48 EDT 2025 Tue Jul 01 01:24:34 EDT 2025 Fri Feb 23 02:49:19 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Batch renormalization Dilated convolution CNN Residual learning Image denoising |
| Language | English |
| License | Copyright © 2019 Elsevier Ltd. All rights reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c362t-ddce8aafecab39ca783a12ce4780de8044bdf6a3c9b01292bfd33923d72b62c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 31629201 |
| PQID | 2307144322 |
| PQPubID | 23479 |
| PageCount | 13 |
| ParticipantIDs | proquest_miscellaneous_2307144322 pubmed_primary_31629201 crossref_primary_10_1016_j_neunet_2019_08_022 crossref_citationtrail_10_1016_j_neunet_2019_08_022 elsevier_sciencedirect_doi_10_1016_j_neunet_2019_08_022 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | January 2020 2020-01-00 2020-Jan 20200101 |
| PublicationDateYYYYMMDD | 2020-01-01 |
| PublicationDate_xml | – month: 01 year: 2020 text: January 2020 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2020 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Guo, Wu, Xu (b20) 2017; 2 Lebrun, Colom, Morel (b36) 2015; 5 Nam, S., Hwang, Y., Matsushita, Y., & Joo Kim, S. (2016). A holistic approach to cross-channel image noise modeling and its application to image denoising. In Zhang, Zuo, Gu, Zhang (b65) 2017; Vol. 2 Dong, Loy, He, Tang (b12) 2016; 38 Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint Chambolle (b5) 2004; 20 Dabov, Foi, Katkovnik, Egiazarian (b11) 2007; 16 Wang, T., Sun, M., & Hu, K. (2017). Dilated residual network for image denoising. arXiv preprint Wen, Xu, Li, Ma, Xu (b57) 2018; 102 Kokkinos, F., & Lefkimmiatis, S. (2018). Iterative residual network for deep joint image demosaicking and denoising. arXiv preprint Xu, J., Li, H., Liang, Z., Zhang, D., & Zhang, L. (2018). Real-world noisy image denoising: A new benchmark. arXiv preprint Chen, J., Chen, J., Chao, H., & Yang, M. (2018). Image blind denoising with generative adversarial network based noise modeling. In Du, Xiong, Wu, Zhang, Zhang, Tao (b16) 2017; 47 (pp. 1586–1595). Kim, J., Kwon Lee, J., & Mu Lee, K. Accurate image super-resolution using very deep convolutional networks. In Chu, Wu, Gu, Xu (b9) 2017 (pp. 3431–3440). Franzen (b18) 1999 Beck, Teboulle (b3) 2009; 18 Rudin, Osher, Fatemi (b49) 1992; 60 Wang, Z., Liu, D., Yang, J., Han, W., & Huang, T. (2015). Deep networks for image super-resolution with sparse prior. In Du, Wei, Liu (b15) 2019 Xu, Zhang, Zhang (b59) 2018; 27 Yu, F., & Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv preprint Li, Yin, Fang (b37) 2012; 59 He, Zhang, Ren, Sun (b21) 2014 Zhang, Zuo (b63) 2017; 34 He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Jiao, Tu, He, Lau (b26) 2017 . Ioffe (b24) 2017 He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Zhang, Wu, Buades, Li (b62) 2011; 20 Kingma, Ba (b29) 2014 Zhang, Zuo, Zhang (b67) 2018; 6 Burger, Schuler, Harmeling (b4) 2012 Dong, W., Wang, P., Yin, W., Shi, G., Wu, F., & Lu, X. (2018). Denoising prior driven deep neural network for image restoration. arXiv preprint Zuo, Zhang, Song, Zhang, Gao (b69) 2014; 23 Chollet (b8) 2015 Dong, Zhang, Shi, Li (b14) 2013; 22 Zhang, Zuo, Chen, Meng, Zhang (b64) 2017; 26 Chen, Pock (b7) 2017; 39 Lai, Huang, Ahuja, Yang (b33) 2017; vol. 2 Fei, Lu, Jia, Teng, Zhang (b17) 2018 Krizhevsky, Sutskever, Hinton (b32) 2012 Lebrun, Colom, Morel (b35) 2015; 24 Roth, Black (b48) 2009; 82 (pp. 1026–1034),. (pp. 1310–1318). Wen, Fang, Xu, Tian, Fei (b56) 2018 Kligvasser, I., Shaham, T. R., & Michaeli, T. (2017). xUnit: Learning a Spatial activation function for efficient image restoration. arXiv preprint Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In (pp. 2862–2869). Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2018). Residual dense network for image super-resolution. In Barbu (b1) 2009 Cruz, C., Foi, A., Katkovnik, V., & Egiazarian, K. (2018). Nonlocality-reinforced convolutional neural networks for image denoising. arXiv preprint Lu, Yuan, Zhu, Li (b40) 2018; 27 Malfait, Roose (b43) 1997; 6 Kim, J., Kwon Lee, J., & Mu Lee, K. (2016). Deeply-recursive convolutional network for image super-resolution. In (pp. 770–778). Barbu (b2) 2009; 18 Schmidt, U., & Roth, S. (2014). Shrinkage fields for effective image restoration. In (pp. 2774–2781). Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014). Weighted nuclear norm minimization with application to image denoising. In (pp. 1637–1645). Mairal, Bach, Ponce, Sapiro, Zisserman (b42) 2009 Zhang, Zuo, Zhang (b66) 2018 Zoran, Weiss (b68) 2011 (pp. 1683–1691). Lin, Milan, Shen, Reid (b38) 2017; Vol. 1 Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., & Anguelov, D., et al. (2015). Going deeper with convolutions. In Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In Ma, Duanmu, Wu, Wang, Yong, Li (b41) 2017; 26 Ren, He, Pu (b47) 2018; 25 (pp. 1–9). Plotz, T., & Roth, S. (2017). Benchmarking denoising algorithms with real photographs. In (pp. 1646–1654). (pp. 3155–3164). Si-Yao, L., Ren, D., Hu, Z., Li, J., Yin, Q., & Guo, P. (2018). A concatenated residual network for image deblurring. arXiv preprint (pp. 370–378). Tai, Yang, Liu (b53) 2017; 1 Latif, Iskandar, Alghazo, Butt, Khan (b34) 2018; 7 Ma (10.1016/j.neunet.2019.08.022_b41) 2017; 26 10.1016/j.neunet.2019.08.022_b46 10.1016/j.neunet.2019.08.022_b44 10.1016/j.neunet.2019.08.022_b45 Lai (10.1016/j.neunet.2019.08.022_b33) 2017; vol. 2 Mairal (10.1016/j.neunet.2019.08.022_b42) 2009 Dong (10.1016/j.neunet.2019.08.022_b12) 2016; 38 Beck (10.1016/j.neunet.2019.08.022_b3) 2009; 18 Kingma (10.1016/j.neunet.2019.08.022_b29) 2014 Franzen (10.1016/j.neunet.2019.08.022_b18) 1999 Rudin (10.1016/j.neunet.2019.08.022_b49) 1992; 60 Zhang (10.1016/j.neunet.2019.08.022_b62) 2011; 20 Wen (10.1016/j.neunet.2019.08.022_b57) 2018; 102 Li (10.1016/j.neunet.2019.08.022_b37) 2012; 59 Du (10.1016/j.neunet.2019.08.022_b15) 2019 10.1016/j.neunet.2019.08.022_b39 Roth (10.1016/j.neunet.2019.08.022_b48) 2009; 82 Malfait (10.1016/j.neunet.2019.08.022_b43) 1997; 6 10.1016/j.neunet.2019.08.022_b31 Zhang (10.1016/j.neunet.2019.08.022_b66) 2018 10.1016/j.neunet.2019.08.022_b30 Burger (10.1016/j.neunet.2019.08.022_b4) 2012 Guo (10.1016/j.neunet.2019.08.022_b20) 2017; 2 Chambolle (10.1016/j.neunet.2019.08.022_b5) 2004; 20 Zhang (10.1016/j.neunet.2019.08.022_b67) 2018; 6 He (10.1016/j.neunet.2019.08.022_b21) 2014 Lu (10.1016/j.neunet.2019.08.022_b40) 2018; 27 Wen (10.1016/j.neunet.2019.08.022_b56) 2018 Lin (10.1016/j.neunet.2019.08.022_b38) 2017; Vol. 1 10.1016/j.neunet.2019.08.022_b28 10.1016/j.neunet.2019.08.022_b27 10.1016/j.neunet.2019.08.022_b25 Dong (10.1016/j.neunet.2019.08.022_b14) 2013; 22 10.1016/j.neunet.2019.08.022_b22 10.1016/j.neunet.2019.08.022_b23 Zuo (10.1016/j.neunet.2019.08.022_b69) 2014; 23 Lebrun (10.1016/j.neunet.2019.08.022_b36) 2015; 5 Xu (10.1016/j.neunet.2019.08.022_b59) 2018; 27 Zhang (10.1016/j.neunet.2019.08.022_b65) 2017; Vol. 2 Lebrun (10.1016/j.neunet.2019.08.022_b35) 2015; 24 10.1016/j.neunet.2019.08.022_b60 10.1016/j.neunet.2019.08.022_b61 Latif (10.1016/j.neunet.2019.08.022_b34) 2018; 7 Tai (10.1016/j.neunet.2019.08.022_b53) 2017; 1 10.1016/j.neunet.2019.08.022_b6 Du (10.1016/j.neunet.2019.08.022_b16) 2017; 47 Dabov (10.1016/j.neunet.2019.08.022_b11) 2007; 16 10.1016/j.neunet.2019.08.022_b19 Krizhevsky (10.1016/j.neunet.2019.08.022_b32) 2012 Fei (10.1016/j.neunet.2019.08.022_b17) 2018 Chu (10.1016/j.neunet.2019.08.022_b9) 2017 10.1016/j.neunet.2019.08.022_b13 10.1016/j.neunet.2019.08.022_b58 Zhang (10.1016/j.neunet.2019.08.022_b64) 2017; 26 Barbu (10.1016/j.neunet.2019.08.022_b1) 2009 10.1016/j.neunet.2019.08.022_b55 10.1016/j.neunet.2019.08.022_b10 10.1016/j.neunet.2019.08.022_b54 10.1016/j.neunet.2019.08.022_b51 10.1016/j.neunet.2019.08.022_b52 Zhang (10.1016/j.neunet.2019.08.022_b63) 2017; 34 10.1016/j.neunet.2019.08.022_b50 Jiao (10.1016/j.neunet.2019.08.022_b26) 2017 Chollet (10.1016/j.neunet.2019.08.022_b8) 2015 Barbu (10.1016/j.neunet.2019.08.022_b2) 2009; 18 Ioffe (10.1016/j.neunet.2019.08.022_b24) 2017 Zoran (10.1016/j.neunet.2019.08.022_b68) 2011 Ren (10.1016/j.neunet.2019.08.022_b47) 2018; 25 Chen (10.1016/j.neunet.2019.08.022_b7) 2017; 39 |
| References_xml | – reference: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In – volume: Vol. 1 start-page: 5 year: 2017 ident: b38 article-title: RefineNet: Multi-path refinement networks for high-resolution semantic segmentation publication-title: CVPR – reference: He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In – reference: (pp. 1646–1654). – volume: 102 start-page: 36 year: 2018 end-page: 47 ident: b57 article-title: Inter-class sparsity based discriminative least square regression publication-title: Neural Networks – year: 2009 ident: b1 article-title: Learning real-time MRF inference for image denoising – start-page: 1945 year: 2017 end-page: 1953 ident: b24 article-title: Batch renormalization: Towards reducing minibatch dependence in batch-normalized models publication-title: Advances in neural information processing systems – reference: Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In – volume: 26 start-page: 3142 year: 2017 end-page: 3155 ident: b64 article-title: Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising publication-title: IEEE Transactions on Image Processing – volume: 23 start-page: 2459 year: 2014 end-page: 2472 ident: b69 article-title: Gradient histogram estimation and preservation for texture enhanced image denoising publication-title: IEEE Transactions on Image Processing – reference: Nam, S., Hwang, Y., Matsushita, Y., & Joo Kim, S. (2016). A holistic approach to cross-channel image noise modeling and its application to image denoising. In – year: 2018 ident: b56 article-title: Low-rank representation with adaptive graph regularization publication-title: Neural Networks – volume: 22 start-page: 1620 year: 2013 end-page: 1630 ident: b14 article-title: Nonlocally centralized sparse representation for image restoration publication-title: IEEE Transactions on Image Processing – volume: 18 start-page: 2451 year: 2009 end-page: 2462 ident: b2 article-title: Training an active random field for real-time image denoising publication-title: IEEE Transactions on Image Processing – reference: (pp. 2862–2869). – start-page: 1097 year: 2012 end-page: 1105 ident: b32 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in neural information processing systems – reference: (pp. 2774–2781). – reference: Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., & Anguelov, D., et al. (2015). Going deeper with convolutions. In – reference: Chen, J., Chen, J., Chao, H., & Yang, M. (2018). Image blind denoising with generative adversarial network based noise modeling. In – volume: 27 start-page: 2996 year: 2018 end-page: 3010 ident: b59 article-title: External prior guided internal prior learning for real-world noisy image denoising publication-title: IEEE Transactions on Image Processing – reference: (pp. 1310–1318). – year: 1999 ident: b18 article-title: Kodak lossless true color image suite – reference: Kim, J., Kwon Lee, J., & Mu Lee, K. (2016). Deeply-recursive convolutional network for image super-resolution. In – volume: 38 start-page: 295 year: 2016 end-page: 307 ident: b12 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 59 start-page: 3450 year: 2012 end-page: 3459 ident: b37 article-title: Group-sparse representation with dictionary learning for medical image denoising and fusion publication-title: IEEE Transactions on Biomedical Engineering – volume: 24 start-page: 3149 year: 2015 end-page: 3161 ident: b35 article-title: Multiscale image blind denoising publication-title: IEEE Transactions on Image Processing – year: 2019 ident: b15 article-title: An improved quantum-behaved particle swarm optimization for endmember extraction publication-title: IEEE Transactions on Geoscience and Remote Sensing – volume: 25 start-page: 916 year: 2018 end-page: 920 ident: b47 article-title: Nonlocal similarity modeling and deep CNN gradient prior for super resolution publication-title: IEEE Signal Processing Letters – reference: Kligvasser, I., Shaham, T. R., & Michaeli, T. (2017). xUnit: Learning a Spatial activation function for efficient image restoration. arXiv preprint – volume: 5 start-page: 1 year: 2015 end-page: 54 ident: b36 article-title: The noise clinic: a blind image denoising algorithm publication-title: Image Processing on Line – reference: (pp. 370–378). – reference: (pp. 1026–1034),. – reference: Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint – volume: 47 start-page: 1017 year: 2017 end-page: 1027 ident: b16 article-title: Stacked convolutional denoising auto-encoders for feature representation publication-title: IEEE Transactions on Cybernetics – start-page: 2272 year: 2009 end-page: 2279 ident: b42 article-title: Non-local sparse models for image restoration publication-title: Computer vision, 2009 IEEE 12th international conference on – reference: Schmidt, U., & Roth, S. (2014). Shrinkage fields for effective image restoration. In – volume: 27 start-page: 5248 year: 2018 end-page: 5260 ident: b40 article-title: Structurally incoherent low-rank nonnegative matrix factorization for image classification publication-title: IEEE Transactions on Image Processing – volume: 26 start-page: 1004 year: 2017 end-page: 1016 ident: b41 article-title: Waterloo exploration database: New challenges for image quality assessment models publication-title: IEEE Transactions on Image Processing – start-page: 605 year: 2017 end-page: 614 ident: b9 article-title: Rich features and precise localization with region proposal network for object detection publication-title: Chinese conference on biometric recognition – volume: vol. 2 start-page: 5 year: 2017 ident: b33 article-title: Deep laplacian pyramid networks for fast and accurate superresolution publication-title: IEEE conference on computer vision and pattern recognition – year: 2018 ident: b66 article-title: FFDNet: Toward a fast and flexible solution for CNN based image denoising publication-title: IEEE Transactions on Image Processing – volume: 39 start-page: 1256 year: 2017 end-page: 1272 ident: b7 article-title: Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 18 start-page: 2419 year: 2009 end-page: 2434 ident: b3 article-title: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems publication-title: IEEE Transactions on Image Processing – reference: (pp. 3155–3164). – volume: 6 year: 2018 ident: b67 article-title: Learning a single convolutional super-resolution network for multiple degradations publication-title: IEEE conference on computer vision and pattern recognition – year: 2018 ident: b17 article-title: Feature extraction methods for palmprint recognition: A survey and evaluation publication-title: IEEE Transactions on Systems, Man, and Cybernetics: Systems – reference: (pp. 1683–1691). – volume: 82 start-page: 205 year: 2009 ident: b48 article-title: Fields of experts publication-title: International Journal of Computer Vision – reference: Xu, J., Li, H., Liang, Z., Zhang, D., & Zhang, L. (2018). Real-world noisy image denoising: A new benchmark. arXiv preprint – volume: 6 start-page: 549 year: 1997 end-page: 565 ident: b43 article-title: Wavelet-based image denoising using a Markov random field a priori model publication-title: IEEE Transactions on Image Processing – volume: 16 start-page: 2080 year: 2007 end-page: 2095 ident: b11 article-title: Image denoising by sparse 3-D transform-domain collaborative filtering publication-title: IEEE Transactions on Image Processing – reference: (pp. 1586–1595). – start-page: 479 year: 2011 end-page: 486 ident: b68 article-title: From learning models of natural image patches to whole image restoration publication-title: Computer vision, 2011 IEEE international conference on – start-page: 2392 year: 2012 end-page: 2399 ident: b4 article-title: Image denoising: Can plain neural networks compete with BM3D? publication-title: Computer vision and pattern recognition, 2012 IEEE conference on – reference: (pp. 1–9). – reference: Cruz, C., Foi, A., Katkovnik, V., & Egiazarian, K. (2018). Nonlocality-reinforced convolutional neural networks for image denoising. arXiv preprint – volume: 7 start-page: 37 year: 2018 end-page: 42 ident: b34 article-title: Deep CNN based MR image denoising for tumor segmentation using watershed transform publication-title: International Journal of Engineering & Technology – reference: Wang, T., Sun, M., & Hu, K. (2017). Dilated residual network for image denoising. arXiv preprint – reference: Si-Yao, L., Ren, D., Hu, Z., Li, J., Yin, Q., & Guo, P. (2018). A concatenated residual network for image deblurring. arXiv preprint – reference: Dong, W., Wang, P., Yin, W., Shi, G., Wu, F., & Lu, X. (2018). Denoising prior driven deep neural network for image restoration. arXiv preprint – reference: Kim, J., Kwon Lee, J., & Mu Lee, K. Accurate image super-resolution using very deep convolutional networks. In – reference: Plotz, T., & Roth, S. (2017). Benchmarking denoising algorithms with real photographs. In – volume: 2 start-page: 39 year: 2017 end-page: 47 ident: b20 article-title: Face recognition using both visible light image and near-infrared image and a deep network publication-title: CAAI Transactions on Intelligence Technology – volume: 20 start-page: 89 year: 2004 end-page: 97 ident: b5 article-title: An algorithm for total variation minimization and applications publication-title: Journal of Mathematical Imaging and Vision – reference: Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014). Weighted nuclear norm minimization with application to image denoising. In – reference: (pp. 770–778). – year: 2015 ident: b8 article-title: Keras: Deep learning library for theano and tensorflow – reference: . – reference: (pp. 1637–1645). – volume: Vol. 2 year: 2017 ident: b65 article-title: Learning deep CNN denoiser prior for image restoration publication-title: IEEE conference on computer vision and pattern recognition – year: 2014 ident: b29 article-title: Adam: A method for stochastic optimization publication-title: Computer Science – volume: 1 start-page: 5 year: 2017 ident: b53 article-title: Image super-resolution via deep recursive residual network publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition – start-page: 1034 year: 2017 end-page: 1042 ident: b26 article-title: Formresnet: formatted residual learning for image restoration publication-title: Computer vision and pattern recognition workshops. 2017 ieee conference on – reference: . – volume: 60 start-page: 259 year: 1992 end-page: 268 ident: b49 article-title: Nonlinear total variation based noise removal algorithms publication-title: Physica D. Nonlinear Phenomena – reference: Wang, Z., Liu, D., Yang, J., Han, W., & Huang, T. (2015). Deep networks for image super-resolution with sparse prior. In – volume: 20 year: 2011 ident: b62 article-title: Color demosaicking by local directional interpolation and nonlocal adaptive thresholding publication-title: Journal of Electronic Imaging – reference: (pp. 3431–3440). – start-page: 346 year: 2014 end-page: 361 ident: b21 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: European conference on computer vision – volume: 34 start-page: 172 year: 2017 end-page: 179 ident: b63 article-title: Image restoration: From sparse and low-rank priors to deep priors [lecture notes] publication-title: IEEE Signal Processing Magazine – reference: Yu, F., & Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv preprint – reference: Kokkinos, F., & Lefkimmiatis, S. (2018). Iterative residual network for deep joint image demosaicking and denoising. arXiv preprint – reference: Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2018). Residual dense network for image super-resolution. In – reference: Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In – volume: 6 year: 2018 ident: 10.1016/j.neunet.2019.08.022_b67 article-title: Learning a single convolutional super-resolution network for multiple degradations – start-page: 605 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b9 article-title: Rich features and precise localization with region proposal network for object detection – ident: 10.1016/j.neunet.2019.08.022_b22 doi: 10.1109/ICCV.2015.123 – volume: 22 start-page: 1620 issue: 4 year: 2013 ident: 10.1016/j.neunet.2019.08.022_b14 article-title: Nonlocally centralized sparse representation for image restoration publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2012.2235847 – volume: 34 start-page: 172 issue: 5 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b63 article-title: Image restoration: From sparse and low-rank priors to deep priors [lecture notes] publication-title: IEEE Signal Processing Magazine doi: 10.1109/MSP.2017.2717489 – volume: 102 start-page: 36 year: 2018 ident: 10.1016/j.neunet.2019.08.022_b57 article-title: Inter-class sparsity based discriminative least square regression publication-title: Neural Networks doi: 10.1016/j.neunet.2018.02.002 – ident: 10.1016/j.neunet.2019.08.022_b54 doi: 10.1109/ICCV.2015.50 – volume: 16 start-page: 2080 issue: 8 year: 2007 ident: 10.1016/j.neunet.2019.08.022_b11 article-title: Image denoising by sparse 3-D transform-domain collaborative filtering publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2007.901238 – start-page: 2272 year: 2009 ident: 10.1016/j.neunet.2019.08.022_b42 article-title: Non-local sparse models for image restoration – volume: 18 start-page: 2451 issue: 11 year: 2009 ident: 10.1016/j.neunet.2019.08.022_b2 article-title: Training an active random field for real-time image denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2009.2028254 – ident: 10.1016/j.neunet.2019.08.022_b27 doi: 10.1109/CVPR.2016.181 – ident: 10.1016/j.neunet.2019.08.022_b10 – year: 2014 ident: 10.1016/j.neunet.2019.08.022_b29 article-title: Adam: A method for stochastic optimization publication-title: Computer Science – volume: 26 start-page: 3142 issue: 7 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b64 article-title: Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2017.2662206 – volume: 5 start-page: 1 year: 2015 ident: 10.1016/j.neunet.2019.08.022_b36 article-title: The noise clinic: a blind image denoising algorithm publication-title: Image Processing on Line doi: 10.5201/ipol.2015.125 – volume: 25 start-page: 916 issue: 7 year: 2018 ident: 10.1016/j.neunet.2019.08.022_b47 article-title: Nonlocal similarity modeling and deep CNN gradient prior for super resolution publication-title: IEEE Signal Processing Letters doi: 10.1109/LSP.2018.2829766 – volume: 60 start-page: 259 issue: 1–4 year: 1992 ident: 10.1016/j.neunet.2019.08.022_b49 article-title: Nonlinear total variation based noise removal algorithms publication-title: Physica D. Nonlinear Phenomena doi: 10.1016/0167-2789(92)90242-F – year: 2015 ident: 10.1016/j.neunet.2019.08.022_b8 – volume: 26 start-page: 1004 issue: 2 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b41 article-title: Waterloo exploration database: New challenges for image quality assessment models publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2016.2631888 – volume: 2 start-page: 39 issue: 1 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b20 article-title: Face recognition using both visible light image and near-infrared image and a deep network publication-title: CAAI Transactions on Intelligence Technology doi: 10.1016/j.trit.2017.03.001 – year: 2018 ident: 10.1016/j.neunet.2019.08.022_b17 article-title: Feature extraction methods for palmprint recognition: A survey and evaluation publication-title: IEEE Transactions on Systems, Man, and Cybernetics: Systems – start-page: 2392 year: 2012 ident: 10.1016/j.neunet.2019.08.022_b4 article-title: Image denoising: Can plain neural networks compete with BM3D? – ident: 10.1016/j.neunet.2019.08.022_b28 – year: 2018 ident: 10.1016/j.neunet.2019.08.022_b66 article-title: FFDNet: Toward a fast and flexible solution for CNN based image denoising publication-title: IEEE Transactions on Image Processing – volume: 47 start-page: 1017 issue: 4 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b16 article-title: Stacked convolutional denoising auto-encoders for feature representation publication-title: IEEE Transactions on Cybernetics doi: 10.1109/TCYB.2016.2536638 – ident: 10.1016/j.neunet.2019.08.022_b45 – volume: 1 start-page: 5 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b53 article-title: Image super-resolution via deep recursive residual network – ident: 10.1016/j.neunet.2019.08.022_b55 – ident: 10.1016/j.neunet.2019.08.022_b30 – ident: 10.1016/j.neunet.2019.08.022_b19 doi: 10.1109/CVPR.2014.366 – ident: 10.1016/j.neunet.2019.08.022_b13 – ident: 10.1016/j.neunet.2019.08.022_b23 doi: 10.1109/CVPR.2016.90 – volume: Vol. 2 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b65 article-title: Learning deep CNN denoiser prior for image restoration – volume: 82 start-page: 205 issue: 2 year: 2009 ident: 10.1016/j.neunet.2019.08.022_b48 article-title: Fields of experts publication-title: International Journal of Computer Vision doi: 10.1007/s11263-008-0197-6 – volume: Vol. 1 start-page: 5 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b38 article-title: RefineNet: Multi-path refinement networks for high-resolution semantic segmentation – ident: 10.1016/j.neunet.2019.08.022_b51 – volume: 23 start-page: 2459 issue: 6 year: 2014 ident: 10.1016/j.neunet.2019.08.022_b69 article-title: Gradient histogram estimation and preservation for texture enhanced image denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2014.2316423 – volume: 20 start-page: 89 issue: 1–2 year: 2004 ident: 10.1016/j.neunet.2019.08.022_b5 article-title: An algorithm for total variation minimization and applications publication-title: Journal of Mathematical Imaging and Vision – volume: 6 start-page: 549 issue: 4 year: 1997 ident: 10.1016/j.neunet.2019.08.022_b43 article-title: Wavelet-based image denoising using a Markov random field a priori model publication-title: IEEE Transactions on Image Processing doi: 10.1109/83.563320 – ident: 10.1016/j.neunet.2019.08.022_b25 – start-page: 1097 year: 2012 ident: 10.1016/j.neunet.2019.08.022_b32 article-title: Imagenet classification with deep convolutional neural networks – year: 2009 ident: 10.1016/j.neunet.2019.08.022_b1 – volume: 38 start-page: 295 issue: 2 year: 2016 ident: 10.1016/j.neunet.2019.08.022_b12 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2015.2439281 – ident: 10.1016/j.neunet.2019.08.022_b31 – start-page: 1945 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b24 article-title: Batch renormalization: Towards reducing minibatch dependence in batch-normalized models – start-page: 1034 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b26 article-title: Formresnet: formatted residual learning for image restoration – volume: 27 start-page: 2996 issue: 6 year: 2018 ident: 10.1016/j.neunet.2019.08.022_b59 article-title: External prior guided internal prior learning for real-world noisy image denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2018.2811546 – year: 2019 ident: 10.1016/j.neunet.2019.08.022_b15 article-title: An improved quantum-behaved particle swarm optimization for endmember extraction publication-title: IEEE Transactions on Geoscience and Remote Sensing doi: 10.1109/TGRS.2019.2903875 – start-page: 346 year: 2014 ident: 10.1016/j.neunet.2019.08.022_b21 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition – ident: 10.1016/j.neunet.2019.08.022_b50 doi: 10.1109/CVPR.2014.349 – ident: 10.1016/j.neunet.2019.08.022_b58 – start-page: 479 year: 2011 ident: 10.1016/j.neunet.2019.08.022_b68 article-title: From learning models of natural image patches to whole image restoration – volume: 7 start-page: 37 issue: 2.3 year: 2018 ident: 10.1016/j.neunet.2019.08.022_b34 article-title: Deep CNN based MR image denoising for tumor segmentation using watershed transform publication-title: International Journal of Engineering & Technology doi: 10.14419/ijet.v7i2.3.9964 – volume: 27 start-page: 5248 issue: 11 year: 2018 ident: 10.1016/j.neunet.2019.08.022_b40 article-title: Structurally incoherent low-rank nonnegative matrix factorization for image classification publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2018.2855433 – year: 1999 ident: 10.1016/j.neunet.2019.08.022_b18 – ident: 10.1016/j.neunet.2019.08.022_b61 doi: 10.1109/CVPR.2018.00262 – ident: 10.1016/j.neunet.2019.08.022_b60 – volume: 24 start-page: 3149 issue: 10 year: 2015 ident: 10.1016/j.neunet.2019.08.022_b35 article-title: Multiscale image blind denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2015.2439041 – ident: 10.1016/j.neunet.2019.08.022_b44 doi: 10.1109/CVPR.2016.186 – ident: 10.1016/j.neunet.2019.08.022_b52 doi: 10.1109/CVPR.2015.7298594 – volume: vol. 2 start-page: 5 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b33 article-title: Deep laplacian pyramid networks for fast and accurate superresolution – volume: 59 start-page: 3450 issue: 12 year: 2012 ident: 10.1016/j.neunet.2019.08.022_b37 article-title: Group-sparse representation with dictionary learning for medical image denoising and fusion publication-title: IEEE Transactions on Biomedical Engineering doi: 10.1109/TBME.2012.2217493 – volume: 39 start-page: 1256 issue: 6 year: 2017 ident: 10.1016/j.neunet.2019.08.022_b7 article-title: Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2016.2596743 – ident: 10.1016/j.neunet.2019.08.022_b39 doi: 10.1109/CVPR.2015.7298965 – year: 2018 ident: 10.1016/j.neunet.2019.08.022_b56 article-title: Low-rank representation with adaptive graph regularization publication-title: Neural Networks doi: 10.1016/j.neunet.2018.08.007 – volume: 20 issue: 2 year: 2011 ident: 10.1016/j.neunet.2019.08.022_b62 article-title: Color demosaicking by local directional interpolation and nonlocal adaptive thresholding publication-title: Journal of Electronic Imaging – volume: 18 start-page: 2419 issue: 11 year: 2009 ident: 10.1016/j.neunet.2019.08.022_b3 article-title: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2009.2028250 – ident: 10.1016/j.neunet.2019.08.022_b6 doi: 10.1109/CVPR.2018.00333 – ident: 10.1016/j.neunet.2019.08.022_b46 doi: 10.1109/CVPR.2017.294 |
| SSID | ssj0006843 |
| Score | 2.6888144 |
| Snippet | Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 461 |
| SubjectTerms | Batch renormalization CNN Deep Learning - standards Dilated convolution Image denoising Pattern Recognition, Automated - methods Residual learning Signal-To-Noise Ratio |
| Title | Image denoising using deep CNN with batch renormalization |
| URI | https://dx.doi.org/10.1016/j.neunet.2019.08.022 https://www.ncbi.nlm.nih.gov/pubmed/31629201 https://www.proquest.com/docview/2307144322 |
| Volume | 121 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8QwEA6LXrz4fqwvInit2yZ95SiLsqvYiyvsLeRVXNHusm6v_nZn0lbxIIJQeigTWibJN5PpNzOEXEZKJLlJdOCiyAYxhqzA7tjAGoXFQHiqfImNhyIdPcV302TaI8MuFwZplS32N5ju0bp9Mmi1OVjMZoPHEExtCg4PuCC-wTdmsMcZrvKrj2-aR5o3zDkQDlC6S5_zHK_K1ZVDRmUkfCFPxn4zT7-5n94M3W6TzdZ_pNfNJ-6Qnqt2yVbXm4G2W3WPiPEbIAUFVJnPMBxAa3-3zi3osCgoxl-pBhx-pkuQAXh-bTMy98nk9mYyHAVtm4TAgPVZBdYalytVOqM0F0ZlOVcRMy7O8tC6PIxjbctUcSM0Rp2YLi0Hr4jbjOmUGX5A1qp55Y4IFZlQcCU2t0msQq1DGyrHMgOnqqgUok94pxxp2hLi2MniVXZcsRfZqFSiSiU2uGSsT4KvUYumhMYf8lmnd_ljKUhA-T9GXnTTJGGX4K8PVbl5_S6R7g5HR44yh838fX0Lj1Js2RUd__u9J2SD4THcR2ZOydpqWbsz8FVW-twvxnOyfj2-HxWfahjoeA |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA5aD3rx_X5F8Lp2N9lXjlIsrY9erNBbyKtYqdui7dXf7kx2V_FQCsKyh2XChknyzWTyZYaQ60iJJDeJDlwU2SDGkBXYHRtYozAZCE-VT7Hx1Es7L_H9IBmskFZ9FwZplRX2l5ju0br60qy02ZyORs3nEExtCg4PuCC-wPcqWYth-WIZg5uvX55HmpfUOZAOULy-P-dJXoWbFw4plZHwmTwZW2SfFvmf3g61t8lm5UDS27KPO2TFFbtkqy7OQKu1ukdE9x2gggKsTEYYD6Bz_7bOTWmr16MYgKUagPiVfoAM4PO4upK5T_rtu36rE1R1EgID5mcWWGtcrtTQGaW5MCrLuYqYcXGWh9blYRxrO0wVN0Jj2InpoeXgFnGbMZ0yww9Io5gU7ohQkQkFT2Jzm8Qq1Dq0oXIsM7CtioZCHBNeK0eaKoc4lrIYy5os9iZLlUpUqcQKl4wdk-Cn1bTMobFEPqv1Lv_MBQkwv6TlVT1MEpYJnn2owk3mnxL57rB35ChzWI7fT194lGLNrujk3_-9JOud_tOjfOz2Hk7JBsM9uQ_TnJHG7GPuzsFxmekLPzG_Acj36gY |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Image+denoising+using+deep+CNN+with+batch+renormalization&rft.jtitle=Neural+networks&rft.au=Tian%2C+Chunwei&rft.au=Xu%2C+Yong&rft.au=Zuo%2C+Wangmeng&rft.date=2020-01-01&rft.eissn=1879-2782&rft.volume=121&rft.spage=461&rft_id=info:doi/10.1016%2Fj.neunet.2019.08.022&rft_id=info%3Apmid%2F31629201&rft.externalDocID=31629201 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |