CubeNet: X-shape connection for camouflaged object detection
•We propose a novel CubeNet architecture for camouflaged object detection, which accompanies with feature Fusion Blocks and X-connection to sufficiently integrate multiple layer features.•The proposed model can be trained quickly. Meanwhile, it achieves real-time inference efficiency.•Extensive resu...
Saved in:
| Published in | Pattern recognition Vol. 127; p. 108644 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.07.2022
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •We propose a novel CubeNet architecture for camouflaged object detection, which accompanies with feature Fusion Blocks and X-connection to sufficiently integrate multiple layer features.•The proposed model can be trained quickly. Meanwhile, it achieves real-time inference efficiency.•Extensive results on three challenging datasets verify the effectiveness of the proposed method.
Camouflaged object detection (COD) aims to detect out-of-attention regions in an image. Current binary segmentation solutions fail to tackle COD easily, since COD is more challenging due to object often accompany with weak boundaries, low contrast, or similar patterns to the background. That is, we need a more efficient scheme to address this problem. In this work, we propose a new COD framework called CubeNet by introducing X connection to the standard encoder-decoder architecture. Specifically, CubeNet consists of two square fusion decoder (SFD) and a sub edge decoder (SED). The special designed SFD takes full advantage of low-level and high-level features extracted from encoder-decoder blocks, providing more powerful representations at each stage. To explicitly modeling the weak boundaries of the objects, we introduced a SED between the two SFD. With such kind of holistic designs, these three decoder modules resolve the challenging ambiguity of camouflaged object detection. CubeNet significantly advance the cutting-edge model on three challenging COD datasets (i.e., COD10K, CAMO, and CHAMELEON), and achieves the real-time (50fps) inference. |
|---|---|
| AbstractList | •We propose a novel CubeNet architecture for camouflaged object detection, which accompanies with feature Fusion Blocks and X-connection to sufficiently integrate multiple layer features.•The proposed model can be trained quickly. Meanwhile, it achieves real-time inference efficiency.•Extensive results on three challenging datasets verify the effectiveness of the proposed method.
Camouflaged object detection (COD) aims to detect out-of-attention regions in an image. Current binary segmentation solutions fail to tackle COD easily, since COD is more challenging due to object often accompany with weak boundaries, low contrast, or similar patterns to the background. That is, we need a more efficient scheme to address this problem. In this work, we propose a new COD framework called CubeNet by introducing X connection to the standard encoder-decoder architecture. Specifically, CubeNet consists of two square fusion decoder (SFD) and a sub edge decoder (SED). The special designed SFD takes full advantage of low-level and high-level features extracted from encoder-decoder blocks, providing more powerful representations at each stage. To explicitly modeling the weak boundaries of the objects, we introduced a SED between the two SFD. With such kind of holistic designs, these three decoder modules resolve the challenging ambiguity of camouflaged object detection. CubeNet significantly advance the cutting-edge model on three challenging COD datasets (i.e., COD10K, CAMO, and CHAMELEON), and achieves the real-time (50fps) inference. |
| ArticleNumber | 108644 |
| Author | Lu, Xiankai Cai, Zhihua Chen, Shuhan Zhuge, Mingchen Guo, Yiyou |
| Author_xml | – sequence: 1 givenname: Mingchen surname: Zhuge fullname: Zhuge, Mingchen email: mczhuge@cug.edu.cn organization: School of Software, Shandong University, China – sequence: 2 givenname: Xiankai surname: Lu fullname: Lu, Xiankai email: luxiankai@sdu.edu.cn organization: School of Software, Shandong University, China – sequence: 3 givenname: Yiyou surname: Guo fullname: Guo, Yiyou email: yiyouguo526@tongji.edu.cn organization: College of Surveying and Geo-Informatics, Tongji University, China – sequence: 4 givenname: Zhihua surname: Cai fullname: Cai, Zhihua email: zhcai@cug.edu.cn organization: School of Computer Science, Chinese University of Geoscience, China – sequence: 5 givenname: Shuhan surname: Chen fullname: Chen, Shuhan email: shchen@yzu.edu.cn organization: School of Information Engineering, Yangzhou University, China |
| BookMark | eNqFkFtLw0AQhRepYFv9Bz7kD6TOXnJpEUGKNyj6ouDbspnM1g1ttmy2gv_ehPjkgz4NzJnvMOfM2KT1LTF2yWHBgedXzeJgIvrtQoAQ_arMlTphU14WMs24EhM2BZA8lQLkGZt1XQPAi16Ysuv1saJniqvkPe0-zIES9G1LGJ1vE-tDgmbvj3ZntlQnvmp6Jakpjgfn7NSaXUcXP3PO3u7vXteP6ebl4Wl9u0lRQh7TEtESEghrEHll0RZGZKqUgqusqKg2XKkqV1QCCANAGS6XRtgSpKRcCjlnq9EXg--6QFaji2b4IAbjdpqDHnrQjR570EMPeuyhh9Uv-BDc3oSv_7CbEaM-2KejoDt01CLVLvTpde3d3wbfLpd7qA |
| CitedBy_id | crossref_primary_10_1016_j_patcog_2024_110895 crossref_primary_10_1109_TCSVT_2022_3178173 crossref_primary_10_1109_TNNLS_2023_3317091 crossref_primary_10_1016_j_inffus_2024_102871 crossref_primary_10_32604_cmc_2024_055327 crossref_primary_10_1016_j_dsp_2024_104403 crossref_primary_10_1007_s00371_024_03688_6 crossref_primary_10_1109_TMM_2023_3291823 crossref_primary_10_1007_s40747_024_01455_7 crossref_primary_10_1016_j_ecoinf_2024_102893 crossref_primary_10_1109_JSEN_2024_3401722 crossref_primary_10_1016_j_cviu_2024_104061 crossref_primary_10_1016_j_neucom_2024_128784 crossref_primary_10_1016_j_neucom_2023_127050 crossref_primary_10_1360_SSI_2022_0138 crossref_primary_10_1109_TPAMI_2024_3438565 crossref_primary_10_1109_JBHI_2023_3305644 crossref_primary_10_1016_j_knosys_2025_113056 crossref_primary_10_1007_s10489_024_05694_6 crossref_primary_10_1016_j_patrec_2023_09_007 crossref_primary_10_1007_s10489_023_04645_x crossref_primary_10_1007_s00521_023_08502_3 crossref_primary_10_1007_s00530_024_01475_w crossref_primary_10_1016_j_jvcir_2024_104208 crossref_primary_10_1007_s11042_024_20371_z crossref_primary_10_1007_s44267_023_00019_6 crossref_primary_10_1109_TCSVT_2022_3197643 crossref_primary_10_1016_j_imavis_2025_105487 crossref_primary_10_1007_s00371_024_03786_5 crossref_primary_10_1016_j_cviu_2025_104321 crossref_primary_10_1016_j_imavis_2024_104973 crossref_primary_10_1007_s11227_024_06376_3 crossref_primary_10_1109_ACCESS_2024_3380893 crossref_primary_10_1016_j_cviu_2023_103719 crossref_primary_10_1109_TCSVT_2023_3245883 crossref_primary_10_1109_TMM_2024_3360710 crossref_primary_10_1007_s11633_022_1365_9 crossref_primary_10_1007_s00530_023_01250_3 crossref_primary_10_3390_math10224219 crossref_primary_10_1016_j_eswa_2024_123558 crossref_primary_10_1007_s00371_022_02611_1 crossref_primary_10_1109_TCSVT_2024_3462465 crossref_primary_10_1007_s13369_024_09888_5 crossref_primary_10_1016_j_engappai_2023_106749 crossref_primary_10_1016_j_engappai_2024_108328 crossref_primary_10_1109_TIP_2024_3449574 crossref_primary_10_1007_s10489_023_04982_x crossref_primary_10_1007_s00530_024_01478_7 crossref_primary_10_32604_cmc_2025_060653 crossref_primary_10_1016_j_imavis_2024_105218 crossref_primary_10_1007_s00371_024_03658_y crossref_primary_10_1007_s00371_025_03805_z crossref_primary_10_1109_TCSVT_2024_3389988 crossref_primary_10_1109_TETCI_2023_3299305 crossref_primary_10_1111_exsy_13444 crossref_primary_10_26599_AIR_2024_9150044 crossref_primary_10_1007_s00138_024_01588_2 crossref_primary_10_1016_j_neucom_2023_126530 crossref_primary_10_1007_s00371_022_02692_y crossref_primary_10_1016_j_imavis_2024_104953 crossref_primary_10_26599_AIR_2023_9150021 crossref_primary_10_1016_j_patcog_2023_109514 crossref_primary_10_1007_s11760_024_03051_1 crossref_primary_10_1109_TCSVT_2023_3308964 |
| Cites_doi | 10.1016/j.patcog.2020.107740 10.1109/TPAMI.2020.3040258 10.1109/TPAMI.2014.2345401 10.1109/TPAMI.2020.3041332 10.1109/TPAMI.2021.3073564 10.1109/TPAMI.2021.3085766 10.1109/JBHI.2021.3138024 10.1016/j.patcog.2021.108023 10.1109/TPAMI.2018.2815688 10.1109/TPAMI.2022.3179526 10.1098/rstb.2008.0217 10.1016/j.cviu.2019.04.006 10.1098/rspb.2013.0064 10.1016/j.patcog.2020.107630 10.1109/TPAMI.2020.3007032 10.1016/j.patcog.2020.107484 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier Ltd |
| Copyright_xml | – notice: 2022 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.patcog.2022.108644 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-5142 |
| ExternalDocumentID | 10_1016_j_patcog_2022_108644 S003132032200125X |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c306t-8ccfece02facc1bfcf7a2548321457beda144b64e8002a00e5c99a2f8033e6323 |
| IEDL.DBID | .~1 |
| ISSN | 0031-3203 |
| IngestDate | Tue Jul 01 02:36:37 EDT 2025 Thu Apr 24 23:06:59 EDT 2025 Fri Feb 23 02:40:37 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Novel feature aggregation Neural network Edge guidance Camouflaged object detection |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c306t-8ccfece02facc1bfcf7a2548321457beda144b64e8002a00e5c99a2f8033e6323 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_patcog_2022_108644 crossref_primary_10_1016_j_patcog_2022_108644 elsevier_sciencedirect_doi_10_1016_j_patcog_2022_108644 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | July 2022 2022-07-00 |
| PublicationDateYYYYMMDD | 2022-07-01 |
| PublicationDate_xml | – month: 07 year: 2022 text: July 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Chen, Pang, Wang, Xiong, Li, Sun, Feng, Liu, Shi, Ouyang (bib0049) 2019 Huang, Wang, Wei, Huang, Shi, Liu, Huang (bib0034) 2020 Zhang, Shi, Zhang (bib0041) 2020; 107 Yang, Zhang, Lu, Ruan, Yang (bib0015) 2013 Chen, Zhu, Papandreou, Schroff, Adam (bib0035) 2018 Chen, Fu, Liu, Chen, Du, Qiu, Shao (bib0055) 2021; 112 (2021). Le, Nguyen, Nie, Tran, Sugimoto (bib0027) 2019; 184 Wang, Lu, Ruan, Yang (bib0019) 2015 Hou, Cheng, Hu, Borji, Tu, Torr (bib0009) 2019 Margolin, Zelnik-Manor, Tal (bib0051) 2014 Zhai, Li, Yang, Chen, Cheng, Fan (bib0031) 2021 Zhu, Liang, Wei, Sun (bib0016) 2014 Qin, Zhang, Huang, Gao, Dehghan, Jagersand (bib0040) 2019 Zhang, Dai, Lu, He, Wang (bib0022) 2018 Fan, Ji, Cheng, Shao (bib0001) 2021 Hall, Cuthill, Baddeley, Shohet, Scott-Samuel (bib0026) 2013; 280 Wu, Su, Huang (bib0048) 2019 Wu, Su, Huang (bib0013) 2019 Lu, Ma, Shen, Yang, Reid, Yang (bib0007) 2020 Zhou, Rahman Siddiquee, Tajbakhsh, Liang (bib0011) 2018 . A. Srivastava, D. Jha, S. Chanda, U. Pal, H.D. Johansen, D. Johansen, M.A. Riegler, S. Ali, P. Halvorsen, MSRF-Net: a multi-scale residual fusion network for biomedical image segmentation, arXiv preprint Zhang, Fan, Dai, Anwar, Saleh, Aliakbarian, Barnes (bib0053) 2021 Zhang, Wang, Lu, Wang, Yin (bib0021) 2017 Fan, Cheng, Liu, Li, Borji (bib0052) 2017 M. Zhuge, D.-P. Fan, N. Liu, D. Zhang, D. Xu, L. Shao, Salient object detection via integrity learning, arXiv preprint Stevens, Merilaita (bib0002) 2009; 364 Sengottuvelan, Wahi, Shanmugam (bib0029) 2008 Ji, Zhu, Zhuge, Fu (bib0030) 2021 Cheng, Mitra, Huang, Torr, Hu (bib0014) 2014; 37 P. Skurowski, H. Abdulameer, J. Baszczyk, T. Depta, A. Kornacki, P. Kozie, Animal camouflage analysis: chameleon database, 2018. Unpublished Manuscript. Zheng, Zhang, Wang, Cao, Sun, Wang (bib0028) 2018; 26 Jiang, Wang, Yuan, Wu, Zheng, Li (bib0018) 2013 Wang, Lai, Fu, Shen, Ling, Yang (bib0024) 2021 Liang, Duan, Ma, Qiao, Miao, Ye (bib0054) 2021; 111 Wang, Song, Duan, Li (bib0038) 2021 Zhao, Shi, Qi, Wang, Jia (bib0044) 2017 Zhao, Wu (bib0047) 2019 Liu, Han, Yang (bib0045) 2018 Fan, Ji, Qin, Cheng (bib0050) 2021 Wei, Wang, Huang (bib0039) 2020; vol. 34 Zhao, Liu, Fan, Cao, Yang, Cheng (bib0012) 2019 Chen, Tan, Wang, Hu (bib0023) 2018 Lu, Wang, Shen, Crandall, Van Gool (bib0056) 2021 Lyu, Zhang, Dai, Aixuan, Liu, Barnes, Fan (bib0032) 2021 Li, Yu (bib0008) 2015 Liu, Hou, Cheng, Feng, Jiang (bib0010) 2019 Wang, Wang, Lu, Zhang, Ruan (bib0020) 2016 Lu, Wang, Shen, Crandall, Luo (bib0005) 2020 Klein, Frintrop (bib0017) 2011 D.-P. Fan, J. Zhang, G. Xu, M.-M. Cheng, L. Shao, Salient objects in clutter Huang, Huang, Gong, Huang, Wang (bib0046) 2019 Lin, Dollar, Girshick, He, Hariharan, Belongie (bib0004) 2017 Woo, Park, Lee, So Kweon (bib0033) 2018 He, Gkioxari, Dollár, Girshick (bib0043) 2017 Krähenbühl, Koltun (bib0036) 2011 Wang, Sun, Cheng, Jiang, Deng, Zhao, Liu, Mu, Tan, Wang (bib0037) 2020 10.1016/j.patcog.2022.108644_bib0042 Klein (10.1016/j.patcog.2022.108644_bib0017) 2011 Huang (10.1016/j.patcog.2022.108644_bib0046) 2019 Zhao (10.1016/j.patcog.2022.108644_bib0044) 2017 Lin (10.1016/j.patcog.2022.108644_bib0004) 2017 Zhu (10.1016/j.patcog.2022.108644_bib0016) 2014 10.1016/j.patcog.2022.108644_bib0003 10.1016/j.patcog.2022.108644_bib0006 Wang (10.1016/j.patcog.2022.108644_bib0037) 2020 Zhang (10.1016/j.patcog.2022.108644_bib0022) 2018 Li (10.1016/j.patcog.2022.108644_bib0008) 2015 Lu (10.1016/j.patcog.2022.108644_bib0005) 2020 Ji (10.1016/j.patcog.2022.108644_bib0030) 2021 Zhao (10.1016/j.patcog.2022.108644_bib0047) 2019 Woo (10.1016/j.patcog.2022.108644_bib0033) 2018 Qin (10.1016/j.patcog.2022.108644_bib0040) 2019 Le (10.1016/j.patcog.2022.108644_bib0027) 2019; 184 Cheng (10.1016/j.patcog.2022.108644_bib0014) 2014; 37 Wang (10.1016/j.patcog.2022.108644_bib0019) 2015 Lu (10.1016/j.patcog.2022.108644_bib0056) 2021 Zhou (10.1016/j.patcog.2022.108644_bib0011) 2018 Wei (10.1016/j.patcog.2022.108644_bib0039) 2020; vol. 34 Wang (10.1016/j.patcog.2022.108644_bib0038) 2021 Fan (10.1016/j.patcog.2022.108644_bib0052) 2017 Stevens (10.1016/j.patcog.2022.108644_bib0002) 2009; 364 Zhang (10.1016/j.patcog.2022.108644_bib0041) 2020; 107 Lyu (10.1016/j.patcog.2022.108644_bib0032) 2021 Margolin (10.1016/j.patcog.2022.108644_bib0051) 2014 Chen (10.1016/j.patcog.2022.108644_bib0023) 2018 Jiang (10.1016/j.patcog.2022.108644_bib0018) 2013 Chen (10.1016/j.patcog.2022.108644_bib0035) 2018 Wu (10.1016/j.patcog.2022.108644_bib0013) 2019 Wang (10.1016/j.patcog.2022.108644_bib0020) 2016 Wu (10.1016/j.patcog.2022.108644_bib0048) 2019 Hall (10.1016/j.patcog.2022.108644_bib0026) 2013; 280 Krähenbühl (10.1016/j.patcog.2022.108644_bib0036) 2011 Chen (10.1016/j.patcog.2022.108644_bib0055) 2021; 112 Sengottuvelan (10.1016/j.patcog.2022.108644_bib0029) 2008 Lu (10.1016/j.patcog.2022.108644_bib0007) 2020 10.1016/j.patcog.2022.108644_bib0025 Chen (10.1016/j.patcog.2022.108644_bib0049) 2019 Liu (10.1016/j.patcog.2022.108644_bib0010) 2019 Zhao (10.1016/j.patcog.2022.108644_bib0012) 2019 Hou (10.1016/j.patcog.2022.108644_bib0009) 2019 Fan (10.1016/j.patcog.2022.108644_bib0001) 2021 Huang (10.1016/j.patcog.2022.108644_bib0034) 2020 Zhang (10.1016/j.patcog.2022.108644_bib0021) 2017 Yang (10.1016/j.patcog.2022.108644_bib0015) 2013 He (10.1016/j.patcog.2022.108644_bib0043) 2017 Zhang (10.1016/j.patcog.2022.108644_bib0053) 2021 Wang (10.1016/j.patcog.2022.108644_bib0024) 2021 Liu (10.1016/j.patcog.2022.108644_bib0045) 2018 Liang (10.1016/j.patcog.2022.108644_bib0054) 2021; 111 Zhai (10.1016/j.patcog.2022.108644_bib0031) 2021 Zheng (10.1016/j.patcog.2022.108644_bib0028) 2018; 26 Fan (10.1016/j.patcog.2022.108644_bib0050) 2021 |
| References_xml | – year: 2020 ident: bib0034 article-title: CCNet: criss-cross attention for semantic segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – volume: 280 start-page: 20130064 year: 2013 ident: bib0026 article-title: Camouflage, detection and identification of moving targets publication-title: Proc. R. Soc. B – volume: 364 start-page: 423 year: 2009 end-page: 427 ident: bib0002 article-title: Animal camouflage: current issues and new perspectives publication-title: Philos. Trans. R. Soc. B – start-page: 108023 year: 2021 ident: bib0038 article-title: EFNet: enhancement-fusion network for semantic segmentation publication-title: Pattern Recognit. – volume: 184 start-page: 45 year: 2019 end-page: 56 ident: bib0027 article-title: Anabranch network for camouflaged object segmentation publication-title: Comput. Vis. Image Understanding – start-page: 1741 year: 2018 end-page: 1750 ident: bib0022 article-title: A bi-directional message passing model for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 4974 year: 2019 end-page: 4983 ident: bib0049 article-title: Hybrid task cascade for instance segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2019 ident: bib0012 article-title: EGNet:Edge guidance network for salient object detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – year: 2021 ident: bib0024 article-title: Salient object detection in the deep learning era: an in-depth survey publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – year: 2021 ident: bib0056 article-title: Segmenting objects from relational visual data publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 6409 year: 2019 end-page: 6418 ident: bib0046 article-title: Mask scoring R-CNN publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2020 ident: bib0007 article-title: Deep object tracking with shrinkage loss publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – reference: D.-P. Fan, J. Zhang, G. Xu, M.-M. Cheng, L. Shao, Salient objects in clutter, – volume: 37 start-page: 569 year: 2014 end-page: 582 ident: bib0014 article-title: Global contrast based salient region detection publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 2214 year: 2011 end-page: 2219 ident: bib0017 article-title: Center-surround divergence of feature statistics for salient object detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 3183 year: 2015 end-page: 3192 ident: bib0019 article-title: Deep networks for saliency detection via local estimation and global search publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 248 year: 2014 end-page: 255 ident: bib0051 article-title: How to evaluate foreground maps? publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2083 year: 2013 end-page: 2090 ident: bib0018 article-title: Salient object detection: a discriminative regional feature integration approach publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2021 ident: bib0032 article-title: Simultaneously localize, segment and rank the camouflaged objects publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 7264 year: 2019 end-page: 7273 ident: bib0013 article-title: Stacked cross refinement network for edge-aware salient object detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 6 year: 2008 end-page: 10 ident: bib0029 article-title: Performance of decamouflaging through exploratory image analysis publication-title: International Conference on Emerging Trends in Engineering and Technology – reference: (2021). – start-page: 825 year: 2016 end-page: 841 ident: bib0020 article-title: Saliency detection with recurrent fully convolutional networks publication-title: European Conference on Computer Vision – year: 2021 ident: bib0031 article-title: Mutual graph learning for camouflaged object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 7479 year: 2019 end-page: 7489 ident: bib0040 article-title: BASNet: boundary-aware salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 234 year: 2018 end-page: 250 ident: bib0023 article-title: Reverse attention for salient object detection publication-title: European Conference on Computer Vision – start-page: 108414 year: 2021 ident: bib0030 article-title: Fast camouflaged object detection via edge-based reversible re-calibration network publication-title: Pattern Recognit. – start-page: 212 year: 2017 end-page: 221 ident: bib0021 article-title: Learning uncertain convolutional features for accurate saliency detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – year: 2021 ident: bib0001 article-title: Concealed object detection publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – reference: (2021). – year: 2018 ident: bib0035 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation publication-title: European Conference on Computer Vision – start-page: 3089 year: 2018 end-page: 3098 ident: bib0045 article-title: PiCANet: learning pixel-wise contextual attention for saliency detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 109 year: 2011 end-page: 117 ident: bib0036 article-title: Efficient inference in fully connected CRFs with Gaussian edge potentials publication-title: NeurIPS – reference: A. Srivastava, D. Jha, S. Chanda, U. Pal, H.D. Johansen, D. Johansen, M.A. Riegler, S. Ali, P. Halvorsen, MSRF-Net: a multi-scale residual fusion network for biomedical image segmentation, arXiv preprint – volume: 111 start-page: 107630 year: 2021 ident: bib0054 article-title: Context-aware network for RGB-D salient object detection publication-title: Pattern Recognit. – year: 2018 ident: bib0033 article-title: CBAM: convolutional block attention module publication-title: European Conference on Computer Vision – volume: vol. 34 start-page: 12321 year: 2020 end-page: 12328 ident: bib0039 article-title: F publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – year: 2020 ident: bib0005 article-title: Zero-shot video object segmentation with co-attention siamese networks publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 5455 year: 2015 end-page: 5463 ident: bib0008 article-title: Visual saliency based on multiscale deep features publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2021 ident: bib0053 article-title: Uncertainty inspired RGB-D saliency detection publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 3166 year: 2013 end-page: 3173 ident: bib0015 article-title: Saliency detection via graph-based manifold ranking publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2814 year: 2014 end-page: 2821 ident: bib0016 article-title: Saliency optimization from robust background detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – reference: P. Skurowski, H. Abdulameer, J. Baszczyk, T. Depta, A. Kornacki, P. Kozie, Animal camouflage analysis: chameleon database, 2018. Unpublished Manuscript. – start-page: 3907 year: 2019 end-page: 3916 ident: bib0048 article-title: Cascaded partial decoder for fast and accurate salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 936 year: 2017 end-page: 944 ident: bib0004 article-title: Feature pyramid networks for object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 6230 year: 2017 end-page: 6239 ident: bib0044 article-title: Pyramid scene parsing network publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2019 ident: bib0009 article-title: Deeply supervised salient object detection with short connections publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – volume: 107 start-page: 107484 year: 2020 ident: bib0041 article-title: Attention and boundary guided salient object detection publication-title: Pattern Recognit. – start-page: 4548 year: 2017 end-page: 4557 ident: bib0052 article-title: Structure-measure: a new way to evaluate foreground maps publication-title: Proceedings of the IEEE International Conference on Computer Vision – reference: . – volume: 112 start-page: 107740 year: 2021 ident: bib0055 article-title: EF-Net: a novel enhancement and fusion network for RGB-D saliency detection publication-title: Pattern Recognit. – start-page: 3 year: 2018 end-page: 11 ident: bib0011 article-title: UNet++: a nested U-Net architecture for medical image segmentation publication-title: DLMIA – year: 2019 ident: bib0010 article-title: A simple pooling-based design for real-time salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 26 start-page: 29 year: 2018 end-page: 33 ident: bib0028 article-title: Detection of people with camouflage pattern via dense deconvolution network publication-title: IEEE SPL – reference: M. Zhuge, D.-P. Fan, N. Liu, D. Zhang, D. Xu, L. Shao, Salient object detection via integrity learning, arXiv preprint – year: 2020 ident: bib0037 article-title: Deep high-resolution representation learning for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – year: 2021 ident: bib0050 article-title: Cognitive vision inspired object segmentation metric and loss function (in Chinese) publication-title: SSI – start-page: 3085 year: 2019 end-page: 3094 ident: bib0047 article-title: Pyramid feature attention network for saliency detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2961 year: 2017 end-page: 2969 ident: bib0043 article-title: Mask R-CNN publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 3183 year: 2015 ident: 10.1016/j.patcog.2022.108644_bib0019 article-title: Deep networks for saliency detection via local estimation and global search – start-page: 6409 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0046 article-title: Mask scoring R-CNN – start-page: 3 year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0011 article-title: UNet++: a nested U-Net architecture for medical image segmentation – start-page: 108414 year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0030 article-title: Fast camouflaged object detection via edge-based reversible re-calibration network publication-title: Pattern Recognit. – year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0035 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation – start-page: 212 year: 2017 ident: 10.1016/j.patcog.2022.108644_bib0021 article-title: Learning uncertain convolutional features for accurate saliency detection – start-page: 825 year: 2016 ident: 10.1016/j.patcog.2022.108644_bib0020 article-title: Saliency detection with recurrent fully convolutional networks – year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0012 article-title: EGNet:Edge guidance network for salient object detection – year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0010 article-title: A simple pooling-based design for real-time salient object detection – year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0033 article-title: CBAM: convolutional block attention module – ident: 10.1016/j.patcog.2022.108644_bib0042 – start-page: 936 year: 2017 ident: 10.1016/j.patcog.2022.108644_bib0004 article-title: Feature pyramid networks for object detection – start-page: 2083 year: 2013 ident: 10.1016/j.patcog.2022.108644_bib0018 article-title: Salient object detection: a discriminative regional feature integration approach – start-page: 4548 year: 2017 ident: 10.1016/j.patcog.2022.108644_bib0052 article-title: Structure-measure: a new way to evaluate foreground maps – volume: 112 start-page: 107740 year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0055 article-title: EF-Net: a novel enhancement and fusion network for RGB-D saliency detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107740 – start-page: 3085 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0047 article-title: Pyramid feature attention network for saliency detection – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0056 article-title: Segmenting objects from relational visual data publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – year: 2020 ident: 10.1016/j.patcog.2022.108644_bib0037 article-title: Deep high-resolution representation learning for visual recognition publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 2814 year: 2014 ident: 10.1016/j.patcog.2022.108644_bib0016 article-title: Saliency optimization from robust background detection – start-page: 3089 year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0045 article-title: PiCANet: learning pixel-wise contextual attention for saliency detection – year: 2020 ident: 10.1016/j.patcog.2022.108644_bib0005 article-title: Zero-shot video object segmentation with co-attention siamese networks publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2020.3040258 – start-page: 7479 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0040 article-title: BASNet: boundary-aware salient object detection – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0031 article-title: Mutual graph learning for camouflaged object detection – start-page: 6230 year: 2017 ident: 10.1016/j.patcog.2022.108644_bib0044 article-title: Pyramid scene parsing network – start-page: 1741 year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0022 article-title: A bi-directional message passing model for salient object detection – start-page: 3166 year: 2013 ident: 10.1016/j.patcog.2022.108644_bib0015 article-title: Saliency detection via graph-based manifold ranking – volume: 26 start-page: 29 issue: 1 year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0028 article-title: Detection of people with camouflage pattern via dense deconvolution network publication-title: IEEE SPL – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0032 article-title: Simultaneously localize, segment and rank the camouflaged objects – volume: 37 start-page: 569 issue: 3 year: 2014 ident: 10.1016/j.patcog.2022.108644_bib0014 article-title: Global contrast based salient region detection publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2014.2345401 – start-page: 6 year: 2008 ident: 10.1016/j.patcog.2022.108644_bib0029 article-title: Performance of decamouflaging through exploratory image analysis – year: 2020 ident: 10.1016/j.patcog.2022.108644_bib0007 article-title: Deep object tracking with shrinkage loss publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2020.3041332 – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0053 article-title: Uncertainty inspired RGB-D saliency detection publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2021.3073564 – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0001 article-title: Concealed object detection publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2021.3085766 – start-page: 109 year: 2011 ident: 10.1016/j.patcog.2022.108644_bib0036 article-title: Efficient inference in fully connected CRFs with Gaussian edge potentials – start-page: 7264 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0013 article-title: Stacked cross refinement network for edge-aware salient object detection – ident: 10.1016/j.patcog.2022.108644_bib0003 doi: 10.1109/JBHI.2021.3138024 – start-page: 108023 year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0038 article-title: EFNet: enhancement-fusion network for semantic segmentation publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2021.108023 – start-page: 234 year: 2018 ident: 10.1016/j.patcog.2022.108644_bib0023 article-title: Reverse attention for salient object detection – year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0009 article-title: Deeply supervised salient object detection with short connections publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2018.2815688 – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0050 article-title: Cognitive vision inspired object segmentation metric and loss function (in Chinese) publication-title: SSI – ident: 10.1016/j.patcog.2022.108644_bib0006 doi: 10.1109/TPAMI.2022.3179526 – ident: 10.1016/j.patcog.2022.108644_bib0025 – volume: 364 start-page: 423 issue: 1516 year: 2009 ident: 10.1016/j.patcog.2022.108644_bib0002 article-title: Animal camouflage: current issues and new perspectives publication-title: Philos. Trans. R. Soc. B doi: 10.1098/rstb.2008.0217 – volume: 184 start-page: 45 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0027 article-title: Anabranch network for camouflaged object segmentation publication-title: Comput. Vis. Image Understanding doi: 10.1016/j.cviu.2019.04.006 – volume: 280 start-page: 20130064 issue: 1758 year: 2013 ident: 10.1016/j.patcog.2022.108644_bib0026 article-title: Camouflage, detection and identification of moving targets publication-title: Proc. R. Soc. B doi: 10.1098/rspb.2013.0064 – start-page: 2214 year: 2011 ident: 10.1016/j.patcog.2022.108644_bib0017 article-title: Center-surround divergence of feature statistics for salient object detection – start-page: 4974 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0049 article-title: Hybrid task cascade for instance segmentation – volume: 111 start-page: 107630 year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0054 article-title: Context-aware network for RGB-D salient object detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107630 – start-page: 3907 year: 2019 ident: 10.1016/j.patcog.2022.108644_bib0048 article-title: Cascaded partial decoder for fast and accurate salient object detection – start-page: 248 year: 2014 ident: 10.1016/j.patcog.2022.108644_bib0051 article-title: How to evaluate foreground maps? – year: 2020 ident: 10.1016/j.patcog.2022.108644_bib0034 article-title: CCNet: criss-cross attention for semantic segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2020.3007032 – volume: vol. 34 start-page: 12321 year: 2020 ident: 10.1016/j.patcog.2022.108644_bib0039 article-title: F3Net: fusion, feedback and focus for salient object detection – volume: 107 start-page: 107484 year: 2020 ident: 10.1016/j.patcog.2022.108644_bib0041 article-title: Attention and boundary guided salient object detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107484 – year: 2021 ident: 10.1016/j.patcog.2022.108644_bib0024 article-title: Salient object detection in the deep learning era: an in-depth survey publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 2961 year: 2017 ident: 10.1016/j.patcog.2022.108644_bib0043 article-title: Mask R-CNN – start-page: 5455 year: 2015 ident: 10.1016/j.patcog.2022.108644_bib0008 article-title: Visual saliency based on multiscale deep features |
| SSID | ssj0017142 |
| Score | 2.6102736 |
| Snippet | •We propose a novel CubeNet architecture for camouflaged object detection, which accompanies with feature Fusion Blocks and X-connection to sufficiently... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 108644 |
| SubjectTerms | Camouflaged object detection Edge guidance Neural network Novel feature aggregation |
| Title | CubeNet: X-shape connection for camouflaged object detection |
| URI | https://dx.doi.org/10.1016/j.patcog.2022.108644 |
| Volume | 127 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF5KvXjxLdYXe_C6Nt1HHuKlFEtV6MlCbmF3M9FKaYOmV3-7O9mkKIiCx4QdCF8m8wjffEPIVR5LAKUVC7UyTBppmImTkHEb5lwIl7F0zbaYhpOZfEhV2iGjdhYGaZVN7PcxvY7WzZ1-g2a_nM9xxhdlBwPnkZizVYoT7DJCL7_-2NA8cL-3VwwXA4an2_G5muNVunC3enZdIuf1yiEpf05PX1LOeI_sNLUiHfrH2ScdWB6Q3XYPA20-y0NyO1obmEJ1Q1P2_qJLoBbpK_XEAnVFKbXaNfjFwoWOnK4M_nmhOVT-wBGZje-eRhPWbEVg1pX3FYutLcBCwAtt7cAUtoi06_LqjUMqMpBr1yOZUAKWgjoIQNkk0byIAyEgFFwck-5ytYQTQrUVOoKgQFU4yW1kEsMdCAJVyKIABj0iWjAy20iG4-aKRdZyw14zD2GGEGYewh5hG6vSS2b8cT5qcc6-vfrMRfVfLU__bXlGtvHK827PSbd6W8OFqy4qc1m7zyXZGt4_Tqaf8SXNzw |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEB5qPejFt1ifOXiN3SbZl3iRYqlae2qht5BkZ7VS2kW3V3-7yT6Kgih43c1A-DaZx_LNfACXSSQQfeXTQPmaCi001VEcUGaChHFuI5Yq2BbDoD8WDxN_0oBu3QvjaJWV7y99euGtqyftCs12Np26Hl83dtCzJ9LFbH-yBuvCXl8nY3D1seJ5OIHvcmQ471C3vO6fK0hemfV3i2dbJjJWaA4J8XN8-hJzejuwVSWL5Lbczy40cL4H27UQA6nu5T7cdJcah5hfkwl9f1EZEuP4K0XLArFZKTHKVvjpzPqOhCy0-_VCEszLBQcw7t2Nun1aySJQY_P7nEbGpGjQY6kypqNTk4bKlnmF5JAfakyULZJ0INDlgsrz0DdxrFgaeZxjwBk_hOZ8MccjIMpwFaKXurFwgplQx5pZELgbQxZ62GkBr8GQppoZ7qQrZrImh73KEkLpIJQlhC2gK6usnJnxx_qwxll--_bSuvVfLY__bXkBG_3R00AO7oePJ7Dp3pQk3FNo5m9LPLOpRq7Pi6P0CdYTz10 |
| 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=CubeNet%3A+X-shape+connection+for+camouflaged+object+detection&rft.jtitle=Pattern+recognition&rft.au=Zhuge%2C+Mingchen&rft.au=Lu%2C+Xiankai&rft.au=Guo%2C+Yiyou&rft.au=Cai%2C+Zhihua&rft.date=2022-07-01&rft.issn=0031-3203&rft.volume=127&rft.spage=108644&rft_id=info:doi/10.1016%2Fj.patcog.2022.108644&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2022_108644 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |