Smoothed dilated convolutions for improved dense prediction
Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding artifacts, which hampers the performance. In this work, we propose two simple ye...
Saved in:
| Published in | Data mining and knowledge discovery Vol. 35; no. 4; pp. 1470 - 1496 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
New York
Springer US
01.07.2021
Springer Nature B.V |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding artifacts, which hampers the performance. In this work, we propose two simple yet effective degridding methods by studying a decomposition of dilated convolutions. Unlike existing models, which explore solutions by focusing on a block of cascaded dilated convolutional layers, our methods address the gridding artifacts by smoothing the dilated convolution itself. In addition, we point out that the two degridding approaches are intrinsically related and define separable and shared (SS) operations, which generalize the proposed methods. We further explore SS operations in view of operations on graphs and propose the SS output layer, which is able to smooth the entire DCNNs by only replacing the output layer. We evaluate our degridding methods and the SS output layer thoroughly, and visualize the smoothing effect through effective receptive field analysis. Results show that our methods degridding yield consistent improvements on the performance of dense prediction tasks, while adding negligible amounts of extra training parameters. And the SS output layer improves the performance by 3.3% and contains only 9% training parameters of the original output layer. |
|---|---|
| AbstractList | Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding artifacts, which hampers the performance. In this work, we propose two simple yet effective degridding methods by studying a decomposition of dilated convolutions. Unlike existing models, which explore solutions by focusing on a block of cascaded dilated convolutional layers, our methods address the gridding artifacts by smoothing the dilated convolution itself. In addition, we point out that the two degridding approaches are intrinsically related and define separable and shared (SS) operations, which generalize the proposed methods. We further explore SS operations in view of operations on graphs and propose the SS output layer, which is able to smooth the entire DCNNs by only replacing the output layer. We evaluate our degridding methods and the SS output layer thoroughly, and visualize the smoothing effect through effective receptive field analysis. Results show that our methods degridding yield consistent improvements on the performance of dense prediction tasks, while adding negligible amounts of extra training parameters. And the SS output layer improves the performance by 3.3% and contains only 9% training parameters of the original output layer. Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding artifacts, which hampers the performance. In this work, we propose two simple yet effective degridding methods by studying a decomposition of dilated convolutions. Unlike existing models, which explore solutions by focusing on a block of cascaded dilated convolutional layers, our methods address the gridding artifacts by smoothing the dilated convolution itself. In addition, we point out that the two degridding approaches are intrinsically related and define separable and shared (SS) operations, which generalize the proposed methods. We further explore SS operations in view of operations on graphs and propose the SS output layer, which is able to smooth the entire DCNNs by only replacing the output layer. We evaluate our degridding methods and the SS output layer thoroughly, and visualize the smoothing effect through effective receptive field analysis. Results show that our methods degridding yield consistent improvements on the performance of dense prediction tasks, while adding negligible amounts of extra training parameters. And the SS output layer improves the performance by 3.3% and contains only 9% training parameters of the original output layer. |
| Author | Ji, Shuiwang Wang, Zhengyang |
| Author_xml | – sequence: 1 givenname: Zhengyang surname: Wang fullname: Wang, Zhengyang organization: Texas A&M University – sequence: 2 givenname: Shuiwang orcidid: 0000-0002-4205-4563 surname: Ji fullname: Ji, Shuiwang email: sji@tamu.edu organization: Texas A&M University |
| BookMark | eNp9UMFKAzEUDFLBtvoDnhY8R99LNptdPEnRKhQ8qOAtrNlEt2w3NUkL_r1ZVxA89PTm8WbeDDMjk971hpBzhEsEkFcBocCSAkOa1kJQcUSmKCSnUhSvk4R5mVNRIpyQWQhrABCMw5RcP22cix-myZq2q2Oa2vV71-1i6_qQWeezdrP1bj8wTB9MtvWmafVwPiXHtu6COfudc_Jyd_u8uKerx-XD4mZFNccq0rxigFoYYyzoAmTF6qqSJc-1ZaxG1ACNKEppjcY3sCgLbBJgrIDGMiv4nFyMf1OOz50JUa3dzvfJUjGR55xhDjyxypGlvQvBG6t0G-shZ_R12ykENVSlxqpUqkr9VKUGA_ZPuvXtpvZfh0V8FIVE7t-N_0t1QPUNpn99EA |
| CitedBy_id | crossref_primary_10_1016_j_bspc_2024_106076 crossref_primary_10_1007_s13042_024_02159_7 crossref_primary_10_1109_ACCESS_2022_3192605 crossref_primary_10_3390_electronics11244211 crossref_primary_10_12677_CSA_2024_141007 crossref_primary_10_3233_AIC_220187 crossref_primary_10_1007_s12046_023_02188_y crossref_primary_10_1017_S1431927622012466 crossref_primary_10_1109_TVLSI_2022_3233882 crossref_primary_10_1007_s11517_022_02702_0 crossref_primary_10_1016_j_neucom_2023_03_061 crossref_primary_10_1007_s10489_022_03382_x crossref_primary_10_1109_TIM_2023_3298653 crossref_primary_10_1002_jbio_202300090 crossref_primary_10_1007_s11554_023_01358_9 crossref_primary_10_1016_j_jag_2023_103632 crossref_primary_10_1007_s00521_022_07553_2 crossref_primary_10_1007_s00530_023_01058_1 crossref_primary_10_1002_mp_17308 crossref_primary_10_3389_fphy_2024_1489245 crossref_primary_10_1155_2024_4337255 crossref_primary_10_3390_s22166054 crossref_primary_10_1049_ipr2_12559 crossref_primary_10_1016_j_trd_2024_104070 crossref_primary_10_34133_plantphenomics_0100 |
| Cites_doi | 10.1109/CVPR.2015.7298965 10.1007/s11263-009-0275-4 10.1109/CVPR.2017.576 10.1109/TPAMI.2017.2699184 10.1109/CVPR.2017.351 10.1109/CVPR.2017.195 10.1109/CVPR.2009.5206848 10.1109/ICCV.2011.6126343 10.1145/3219819.3219947 10.1109/78.157290 10.1109/ICIP.2013.6738831 10.1109/WACV.2018.00163 10.1109/WACV.2018.00162 10.1007/978-3-319-10602-1_48 10.1109/CVPR.2017.660 10.1109/CVPR.2015.7298636 10.1109/CVPR.2016.90 10.1145/3219819.3219944 10.1109/CVPR.2017.75 10.1109/CVPR.2016.350 10.1007/978-3-642-33266-1_8 10.1007/978-3-642-75988-8_28 |
| ContentType | Journal Article |
| Copyright | The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2021 The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2021. |
| Copyright_xml | – notice: The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2021 – notice: The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2021. |
| DBID | AAYXX CITATION 3V. 7SC 7WY 7WZ 7XB 87Z 8AL 8AO 8FD 8FE 8FG 8FK 8FL 8G5 ABUWG AFKRA ARAPS AZQEC BENPR BEZIV BGLVJ CCPQU DWQXO FRNLG F~G GNUQQ GUQSH HCIFZ JQ2 K60 K6~ K7- L.- L7M L~C L~D M0C M0N M2O MBDVC P5Z P62 PHGZM PHGZT PKEHL PQBIZ PQBZA PQEST PQGLB PQQKQ PQUKI Q9U |
| DOI | 10.1007/s10618-021-00765-5 |
| DatabaseName | CrossRef ProQuest Central (Corporate) Computer and Information Systems Abstracts ABI/INFORM Collection ABI/INFORM Global (PDF only) ProQuest Central (purchase pre-March 2016) ABI/INFORM Collection Computing Database (Alumni Edition) ProQuest Pharma Collection Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) ABI/INFORM Collection (Alumni) ProQuest Research Library ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Central Business Premium Collection Technology Collection ProQuest One Community College ProQuest Central Korea Business Premium Collection (Alumni) ABI/INFORM Global (Corporate) ProQuest Central Student ProQuest Research Library SciTech Premium Collection ProQuest Computer Science Collection ProQuest Business Collection (Alumni Edition) ProQuest Business Collection Computer Science Database ABI/INFORM Professional Advanced Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ABI/INFORM Global Computing Database ProQuest Research Library Research Library (Corporate) Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic ProQuest One Academic Middle East (New) ProQuest One Business ProQuest One Business (Alumni) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central Basic |
| DatabaseTitle | CrossRef ABI/INFORM Global (Corporate) ProQuest Business Collection (Alumni Edition) ProQuest One Business Research Library Prep Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College Research Library (Alumni Edition) ProQuest Pharma Collection ABI/INFORM Complete ProQuest Central ABI/INFORM Professional Advanced ProQuest One Applied & Life Sciences ProQuest Central Korea ProQuest Research Library ProQuest Central (New) Advanced Technologies Database with Aerospace ABI/INFORM Complete (Alumni Edition) Advanced Technologies & Aerospace Collection Business Premium Collection ABI/INFORM Global ProQuest Computing ABI/INFORM Global (Alumni Edition) ProQuest Central Basic ProQuest Computing (Alumni Edition) ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection ProQuest Business Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition ProQuest One Business (Alumni) ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) Business Premium Collection (Alumni) |
| DatabaseTitleList | ABI/INFORM Global (Corporate) |
| Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Physics Computer Science |
| EISSN | 1573-756X |
| EndPage | 1496 |
| ExternalDocumentID | 10_1007_s10618_021_00765_5 |
| GrantInformation_xml | – fundername: Division of Information and Intelligent Systems grantid: 1633359 funderid: http://dx.doi.org/10.13039/100000145 – fundername: Defense Advanced Research Projects Agency grantid: N66001-17-2-4031 funderid: http://dx.doi.org/10.13039/100000185 |
| GroupedDBID | -59 -5G -BR -EM -Y2 -~C .4S .86 .DC .VR 06D 0R~ 0VY 199 1N0 1SB 203 29F 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 3V. 4.4 406 408 409 40D 40E 5GY 5VS 67Z 6NX 78A 7WY 8AO 8FE 8FG 8FL 8G5 8TC 8UJ 95- 95. 95~ 96X AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC B-. BA0 BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EBLON EBS EDO EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 GROUPED_ABI_INFORM_COMPLETE GUQSH GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X J-C J0Z J9A JBSCW JCJTX JZLTJ K60 K6V K6~ K7- KDC KOV LAK LLZTM M0C M0N M2O M4Y MA- N2Q NB0 NPVJJ NQJWS NU0 O9- O93 O9J OAM OVD P2P P62 P9O PF0 PQBIZ PQBZA PQQKQ PROAC PT4 PT5 Q2X QOS R89 R9I RNI RNS ROL RPX RSV RZC RZE RZK S16 S1Z S27 S3B SAP SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TEORI TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z7R Z7S Z7W Z7X Z7Y Z7Z Z81 Z83 Z88 ZMTXR AAPKM AAYXX ABBRH ABDBE ABFSG ACSTC ADHKG ADKFA AEZWR AFDZB AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP AMVHM ATHPR AYFIA CITATION PHGZM PHGZT 7SC 7XB 8AL 8FD 8FK ABRTQ JQ2 L.- L7M L~C L~D MBDVC PKEHL PQEST PQGLB PQUKI Q9U |
| ID | FETCH-LOGICAL-c319t-49201c5eeef0c60792a997834cf22a11c00d5687fec1b0f1761d1b02260df2f53 |
| IEDL.DBID | BENPR |
| ISSN | 1384-5810 |
| IngestDate | Sat Aug 16 17:22:40 EDT 2025 Tue Jul 01 00:40:32 EDT 2025 Thu Apr 24 23:03:39 EDT 2025 Fri Feb 21 02:47:47 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | Deep learning Dilated convolutions Gridding artifacts |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-49201c5eeef0c60792a997834cf22a11c00d5687fec1b0f1761d1b02260df2f53 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-4205-4563 |
| PQID | 2544321403 |
| PQPubID | 43030 |
| PageCount | 27 |
| ParticipantIDs | proquest_journals_2544321403 crossref_citationtrail_10_1007_s10618_021_00765_5 crossref_primary_10_1007_s10618_021_00765_5 springer_journals_10_1007_s10618_021_00765_5 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 20210700 2021-07-00 20210701 |
| PublicationDateYYYYMMDD | 2021-07-01 |
| PublicationDate_xml | – month: 7 year: 2021 text: 20210700 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Data mining and knowledge discovery |
| PublicationTitleAbbrev | Data Min Knowl Disc |
| PublicationYear | 2021 |
| Publisher | Springer US Springer Nature B.V |
| Publisher_xml | – name: Springer US – name: Springer Nature B.V |
| References | Gao H, Wang Z, Ji S (2018) Large-scale learnable graph convolutional networks. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1416–1424 Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 1251–1258 Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation. In: Proceedings of the IEEE winter conference on applications of computer vision. IEEE, pp 1451–1460 Giusti A, Cireşan DC, Masci J, Gambardella LM, Schmidhuber J (2013) Fast image scanning with deep max-pooling convolutional neural networks. In: Proceedings of the IEEE international conference on image processing. IEEE, pp 4034–4038 Mamalet F, Garcia C (2012) Simplifying convnets for fast learning. In: Proceedings of the international conference on artificial neural networks. Springer, pp 58–65 Oord Avd, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 2881–2890 Holschneider M, Kronland-Martinet R, Morlet J, Tchamitchian P (1990) A real-time algorithm for signal analysis with the help of the wavelet transform. In: Wavelets. Springer, pp 286–297 Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 3431–3440 Monti F, Boscaini D, Masci J, Rodola E, Svoboda J, Bronstein MM (2017) Geometric deep learning on graphs and manifolds using mixture model CNNs. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 5115–5124 Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Lecun Y (2014) Overfeat: Integrated recognition, localization and detection using convolutional networks. In: Proceedings of the international conference on learning representations Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M et al (2016) Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th {\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\{$$\end{document}USENIX}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\}$$\end{document} symposium on operating systems design and implementation. pp 265–283 Hamaguchi R, Fujita A, Nemoto K, Imaizumi T, Hikosaka S (2018) Effective use of dilated convolutions for segmenting small object instances in remote sensing imagery. In: Proceedings of the IEEE winter conference on applications of computer vision. IEEE, pp 1442–1450 Yu F, Koltun V, Funkhouser T (2017) Dilated residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 472–480 Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: Proceedings of the international conference on learning representations Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I, Wojna Z, Song Y, Guadarrama S et al (2017) Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 7310–7311 Papandreou G, Kokkinos I, Savalle PA (2015) Modeling local and global deformations in deep learning: epitomic convolution, multiple instance learning, and sliding window detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 390–399 He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 770–778 Li H, Zhao R, Wang X (2014) Highly efficient forward and backward propagation of convolutional neural networks for pixelwise classification. arXiv preprint arXiv:1412.4526 Ziegler T, Fritsche M, Kuhn L, Donhauser K (2019) Efficient smoothing of dilated convolutions for image segmentation. arXiv preprint arXiv:1903.07992 Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 248–255 Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proceedings of the European conference on computer vision. Springer, pp 740–755 EveringhamMVan GoolLWilliamsCKWinnJZissermanAThe pascal visual object classes (voc) challengeInt J Comput Vis201088230333810.1007/s11263-009-0275-4 Hariharan B, Arbeláez P, Bourdev L, Maji S, Malik J (2011) Semantic contours from inverse detectors. In: Proceedings of the IEEE international conference on computer vision. IEEE, pp 991–998 Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 3213–3223 Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. In: Advances in neural information processing systems. pp 379–387 Wang Z, Ji S (2018) Smoothed dilated convolutions for improved dense prediction. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 2486–2495 Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017a) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848 Chen LC, Papandreou G, Schroff F, Adam H (2017b) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 Kalchbrenner N, Espeholt L, Simonyan K, Oord Avd, Graves A, Kavukcuoglu K (2016) Neural machine translation in linear time. arXiv preprint arXiv:1610.10099 Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Advances in neural information processing systems. pp 4898–4906 Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: Proceedings of the international conference on learning representations ShensaMJThe discrete wavelet transform: wedding the a trous and Mallat algorithmsIEEE Trans Signal Process199240102464248210.1109/78.157290 Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in neural information processing systems. pp 1024–1034 Kalchbrenner N, van den Oord A, Simonyan K, Danihelka I, Vinyals O, Graves A, Kavukcuoglu K (2017) Video pixel networks. In: Proceedings of the international conference on machine learning. pp 1771–1779 GaoHYuanHWangZJiSPixel transposed convolutional networksIEEE Trans Pattern Anal Mach Intell201942512181227 Liu W, Rabinovich A, Berg AC (2015) Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579 765_CR15 765_CR37 765_CR16 765_CR17 765_CR18 765_CR11 765_CR33 765_CR12 765_CR34 765_CR13 765_CR35 765_CR14 765_CR36 765_CR31 765_CR32 M Everingham (765_CR8) 2010; 88 765_CR9 765_CR26 765_CR27 765_CR28 765_CR29 765_CR22 765_CR23 765_CR24 765_CR25 765_CR3 765_CR2 765_CR1 765_CR20 765_CR21 765_CR7 765_CR6 765_CR5 765_CR4 MJ Shensa (765_CR30) 1992; 40 H Gao (765_CR10) 2019; 42 765_CR19 |
| References_xml | – reference: Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in neural information processing systems. pp 1024–1034 – reference: Monti F, Boscaini D, Masci J, Rodola E, Svoboda J, Bronstein MM (2017) Geometric deep learning on graphs and manifolds using mixture model CNNs. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 5115–5124 – reference: Ziegler T, Fritsche M, Kuhn L, Donhauser K (2019) Efficient smoothing of dilated convolutions for image segmentation. arXiv preprint arXiv:1903.07992 – reference: Papandreou G, Kokkinos I, Savalle PA (2015) Modeling local and global deformations in deep learning: epitomic convolution, multiple instance learning, and sliding window detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 390–399 – reference: Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017a) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848 – reference: Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 1251–1258 – reference: Liu W, Rabinovich A, Berg AC (2015) Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579 – reference: Chen LC, Papandreou G, Schroff F, Adam H (2017b) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 – reference: Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 3213–3223 – reference: Wang Z, Ji S (2018) Smoothed dilated convolutions for improved dense prediction. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 2486–2495 – reference: Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: Proceedings of the international conference on learning representations – reference: Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I, Wojna Z, Song Y, Guadarrama S et al (2017) Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 7310–7311 – reference: Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proceedings of the European conference on computer vision. Springer, pp 740–755 – reference: Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M et al (2016) Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th {\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\{$$\end{document}USENIX}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\}$$\end{document} symposium on operating systems design and implementation. pp 265–283 – reference: Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Lecun Y (2014) Overfeat: Integrated recognition, localization and detection using convolutional networks. In: Proceedings of the international conference on learning representations – reference: Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. In: Advances in neural information processing systems. pp 379–387 – reference: Giusti A, Cireşan DC, Masci J, Gambardella LM, Schmidhuber J (2013) Fast image scanning with deep max-pooling convolutional neural networks. In: Proceedings of the IEEE international conference on image processing. IEEE, pp 4034–4038 – reference: Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 248–255 – reference: Hariharan B, Arbeláez P, Bourdev L, Maji S, Malik J (2011) Semantic contours from inverse detectors. In: Proceedings of the IEEE international conference on computer vision. IEEE, pp 991–998 – reference: Mamalet F, Garcia C (2012) Simplifying convnets for fast learning. In: Proceedings of the international conference on artificial neural networks. Springer, pp 58–65 – reference: Kalchbrenner N, Espeholt L, Simonyan K, Oord Avd, Graves A, Kavukcuoglu K (2016) Neural machine translation in linear time. arXiv preprint arXiv:1610.10099 – reference: Li H, Zhao R, Wang X (2014) Highly efficient forward and backward propagation of convolutional neural networks for pixelwise classification. arXiv preprint arXiv:1412.4526 – reference: EveringhamMVan GoolLWilliamsCKWinnJZissermanAThe pascal visual object classes (voc) challengeInt J Comput Vis201088230333810.1007/s11263-009-0275-4 – reference: Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 2881–2890 – reference: Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Advances in neural information processing systems. pp 4898–4906 – reference: Oord Avd, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 – reference: Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation. In: Proceedings of the IEEE winter conference on applications of computer vision. IEEE, pp 1451–1460 – reference: Kalchbrenner N, van den Oord A, Simonyan K, Danihelka I, Vinyals O, Graves A, Kavukcuoglu K (2017) Video pixel networks. In: Proceedings of the international conference on machine learning. pp 1771–1779 – reference: Yu F, Koltun V, Funkhouser T (2017) Dilated residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 472–480 – reference: Hamaguchi R, Fujita A, Nemoto K, Imaizumi T, Hikosaka S (2018) Effective use of dilated convolutions for segmenting small object instances in remote sensing imagery. In: Proceedings of the IEEE winter conference on applications of computer vision. IEEE, pp 1442–1450 – reference: Holschneider M, Kronland-Martinet R, Morlet J, Tchamitchian P (1990) A real-time algorithm for signal analysis with the help of the wavelet transform. In: Wavelets. Springer, pp 286–297 – reference: Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 3431–3440 – reference: Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: Proceedings of the international conference on learning representations – reference: Gao H, Wang Z, Ji S (2018) Large-scale learnable graph convolutional networks. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1416–1424 – reference: GaoHYuanHWangZJiSPixel transposed convolutional networksIEEE Trans Pattern Anal Mach Intell201942512181227 – reference: He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 770–778 – reference: ShensaMJThe discrete wavelet transform: wedding the a trous and Mallat algorithmsIEEE Trans Signal Process199240102464248210.1109/78.157290 – ident: 765_CR23 doi: 10.1109/CVPR.2015.7298965 – ident: 765_CR29 – volume: 88 start-page: 303 issue: 2 year: 2010 ident: 765_CR8 publication-title: Int J Comput Vis doi: 10.1007/s11263-009-0275-4 – ident: 765_CR26 doi: 10.1109/CVPR.2017.576 – ident: 765_CR2 doi: 10.1109/TPAMI.2017.2699184 – ident: 765_CR6 – ident: 765_CR19 – ident: 765_CR37 – ident: 765_CR31 – ident: 765_CR17 doi: 10.1109/CVPR.2017.351 – ident: 765_CR4 doi: 10.1109/CVPR.2017.195 – ident: 765_CR7 doi: 10.1109/CVPR.2009.5206848 – ident: 765_CR14 doi: 10.1109/ICCV.2011.6126343 – ident: 765_CR9 doi: 10.1145/3219819.3219947 – volume: 40 start-page: 2464 issue: 10 year: 1992 ident: 765_CR30 publication-title: IEEE Trans Signal Process doi: 10.1109/78.157290 – ident: 765_CR11 doi: 10.1109/ICIP.2013.6738831 – ident: 765_CR33 doi: 10.1109/WACV.2018.00163 – volume: 42 start-page: 1218 issue: 5 year: 2019 ident: 765_CR10 publication-title: IEEE Trans Pattern Anal Mach Intell – ident: 765_CR27 – ident: 765_CR3 – ident: 765_CR12 doi: 10.1109/WACV.2018.00162 – ident: 765_CR21 doi: 10.1007/978-3-319-10602-1_48 – ident: 765_CR1 – ident: 765_CR36 doi: 10.1109/CVPR.2017.660 – ident: 765_CR28 doi: 10.1109/CVPR.2015.7298636 – ident: 765_CR15 doi: 10.1109/CVPR.2016.90 – ident: 765_CR13 – ident: 765_CR18 – ident: 765_CR32 doi: 10.1145/3219819.3219944 – ident: 765_CR34 – ident: 765_CR35 doi: 10.1109/CVPR.2017.75 – ident: 765_CR5 doi: 10.1109/CVPR.2016.350 – ident: 765_CR25 doi: 10.1007/978-3-642-33266-1_8 – ident: 765_CR22 – ident: 765_CR16 doi: 10.1007/978-3-642-75988-8_28 – ident: 765_CR20 – ident: 765_CR24 |
| SSID | ssj0005230 |
| Score | 2.4901443 |
| Snippet | Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction... Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1470 |
| SubjectTerms | Artificial Intelligence Artificial neural networks Chemistry and Earth Sciences Computer Science Convolution Data Mining and Knowledge Discovery Decomposition Deep learning Information Storage and Retrieval Neural networks Parameters Performance enhancement Physics Semantics Smoothing Statistics for Engineering Training |
| SummonAdditionalLinks | – databaseName: SpringerLink Journals (ICM) dbid: U2A link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB60InjxURWrVXLwpoEkm2R38VTEUgS9aKG3JZsHFGqVtv5_M9tdW0UFbwt5HCaZzZfM980AXCZSWJcZQROXSipLzalJlaKptqJE5SJ3qB1-eNSDobwfqVEtCps3bPcmJFn9qdfEbppnFCkFGD5SVG3Clop3dyRyDUVvjdiRLLXBmaQq46yWyvw8x9fjaIUxv4VFq9Omvw-7NUwkveW6HsCGn7ZhrynBQGqPbMN2xeC080O4eXp5RTWVI248iQDSESSUNxuLRGxKxtUDAvaId1dP3mYYpMHmIxj2755vB7SujEBtdJkFlXk8t63y3gdmNUtzYXJ8w5E2CGE4t4w5pbM0eMtLFniquYsfEWoxF0RQyTG0pq9TfwJEGWcjClPRWYzU2mQs5DaoXLnElSY3HeCNgQpbpw3H6hWTYpXwGI1aRKMWlVEL1YGrzzFvy6QZf_buNnYvageaF5g5DWsosaQD181arJp_n-30f93PYEdU2wEJuF1oLWbv_jzCjEV5Ue2qD98Axf4 priority: 102 providerName: Springer Nature |
| Title | Smoothed dilated convolutions for improved dense prediction |
| URI | https://link.springer.com/article/10.1007/s10618-021-00765-5 https://www.proquest.com/docview/2544321403 |
| Volume | 35 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NS8MwFH_odvHitzidowdvGkzSJk3xIFM2RXGIOpinkiYtDOY2df7_5nWpU8HdSpPm8F7ee7--T4DjMOLGKs1JaOOIRJlkRMdCkFganmHlIrNYO3zfkzf96HYgBt7h9uHTKiudWCpqOzHoIz_DVlo4VIeGF9M3glOjMLrqR2isQt2pYKVqUL_s9B4efyR5hPM6YRURoRj1ZTO-eE4yRTBFAcNRgojfpmmBN_-ESEvL092EdQ8Zg_acx1uwko-3YaMaxxB46dyB86fXCdZT2cAORw5C2gBTyqurFTh0GgxLFwLucH-veTB9xzANLu9Cv9t5vrohfjYCMU5oZiRKnOU2Is_zghpJ44TrBL04kSk414wZSq2QKi5ywzJasFgy6x4c2KK24IUI96A2nozzfQiEtsbhMOHERUdSakWLxBQiETa0mU50A1hFltT4xuE4v2KULloeIylTR8q0JGUqGnDy_c103jZj6e5mRe3Ui9BHumB4A04rDiyW_z_tYPlph7DGS6Zjym0TarP3z_zIAYtZ1oJV1b1uQb19_XLXafm75N72efsLB5fKyQ |
| linkProvider | ProQuest |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LSwMxEB6KHvTiW6zPHPSkwSSb7AMREbVWbXtRwduaTbIgaFu1Iv4pf6OZ7a5VQW_eFpLNYfJlZpKZbwZgM5DC2FgLGthIUpmFnOpIKRqFRmTIXOQWucPtTti8luc36qYG7xUXBtMqK51YKGrbM_hGvoultLCpDgsO-o8Uu0ZhdLVqoTGExYV7e_VXtuf9s2O_v1tCNE6ujpq07CpAjYfbgMrE2zyjnHM5MyGLEqETfP-QJhdCc24YsyqMo9wZnrGc-3u-9R_eTWE2Fzl2ifAqf1wG3pIjM71x-iWlJBiykmNJVcxZSdIpqXohjykmRGDwS1H13RCOvNsfAdnCzjVmYKp0UMnhEFGzUHPdOZiumj-QUhfMw97lQw_ZW5bYu3vvsFqCCewVkIn3hcld8WCBM_xd2ZH-EwaFcHgBrv9FZosw1u113RIQpa3xXp_yh1PLMNQxyxOTq0TZwGY60XXglVhSU5Ypx24Z9-mowDKKMvWiTAtRpqoO25__9IdFOv6cvVpJOy0P7HM6glcddqodGA3_vtry36ttwETzqt1KW2edixWYFAUAMNl3FcYGTy9uzbs0g2y9wBGB2_8G7gdSKAHT |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LTxsxEB6hICEuLYVWDU8f4EQtbO96H0IIUUjEM4pokbhtvX5IkWgSIAj1r_XX4dl4SYtEbrmtZK8P48_jbzwvgO0oFtpkStDIpDGNy4RTlUpJ00SLEjMXucHc4atOcnoTn9_K2zn4W-fCYFhlrRMrRW0GGt_I97CUFjbVYdGeC2ER3ZP24fCeYgcp9LTW7TTGELmwf569-fZ4cHbi93pHiHbr5_EpDR0GqPbQG9E49_efltZax3TC0lyoHN9CYu2EUJxrxoxMstRZzUvmuLf5jf_wlIUZJxx2jPDqfz5Fq6gB899bne71PwEm0ThHOYupzDgLKTshcS_hGcXwCHSFSSr_vxYnXPeNe7a69dpL8CHQVXI0xtcnmLP9ZfhYt4IgQTOswP6P3wPM5TLE9O48fTUEw9lrWBPPjEmver7AGd5ytmT4gC4iHP4MNzOR2hdo9Ad9-xWIVEZ7Dij9UVVxkqiMuVw7mUsTmVLlqgm8FkuhQ9Fy7J1xV0zKLaMoCy_KohJlIZuw-_rPcFyyY-rs9VraRTi-j8UEbE34Vu_AZPj91Vanr7YFCx60xeVZ52INFkW1_xj5uw6N0cOT3fD8ZlRuBiAR-DVr7L4A3fIHZQ |
| 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=Smoothed+dilated+convolutions+for+improved+dense+prediction&rft.jtitle=Data+mining+and+knowledge+discovery&rft.au=Wang+Zhengyang&rft.au=Ji+Shuiwang&rft.date=2021-07-01&rft.pub=Springer+Nature+B.V&rft.issn=1384-5810&rft.eissn=1573-756X&rft.volume=35&rft.issue=4&rft.spage=1470&rft.epage=1496&rft_id=info:doi/10.1007%2Fs10618-021-00765-5&rft.externalDBID=HAS_PDF_LINK |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1384-5810&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1384-5810&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1384-5810&client=summon |