{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T06:15:22Z","timestamp":1759385722645,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093466","type":"proceedings-article","created":{"date-parts":[[2020,5,14]],"date-time":"2020-05-14T23:41:09Z","timestamp":1589499669000},"page":"1044-1048","source":"Crossref","is-referenced-by-count":9,"title":["Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters"],"prefix":"10.1109","author":[{"given":"Ziming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenchi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanwei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"6","article-title":"Near-orthogonality regularization in kernel methods","volume":"3","author":"xie","year":"2017","journal-title":"UAI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.539"},{"key":"ref33","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"NeurIPS"},{"article-title":"Regularizing cnns with locally constrained decor-relations","year":"2016","author":"rodr\u00edguez","key":"ref32"},{"key":"ref31","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"qi","year":"2017","journal-title":"CVPR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref37","first-page":"1912","article-title":"3d shapenets: A deep representation for volumetric shapes","author":"wu","year":"2015","journal-title":"CVPR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00136"},{"key":"ref35","first-page":"3570","article-title":"On orthogonality and learning recurrent networks with long term dependencies","author":"vorontsov","year":"2017","journal-title":"ICML"},{"article-title":"L2 regularization versus batch and weight normalization","year":"2017","author":"van laarhoven","key":"ref34"},{"article-title":"Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning","year":"2018","author":"martin","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545693"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"year":"0","key":"ref2"},{"year":"0","key":"ref1"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"ioffe","key":"ref20"},{"article-title":"The cifar-10 dataset","year":"2014","author":"krizhevsky","key":"ref22"},{"article-title":"Orthogonal deep neural networks","year":"2019","author":"jia","key":"ref21"},{"article-title":"Interpretable Convolutional Neural Networks via Feedforward Design","year":"2018","author":"kuo","key":"ref24"},{"article-title":"Regularization for deep learning: A taxonomy","year":"2017","author":"kuka?ka","key":"ref23"},{"key":"ref26","first-page":"107149","article-title":"Mdfn: Multi-scale deep feature learning network for object detection","author":"ma","year":"2019","journal-title":"Pattern Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/453"},{"article-title":"Deep multi-view learning with stochastic decorrelation loss","year":"2017","author":"chang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/509961.509965"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.07.051"},{"article-title":"Reducing overfitting in deep networks by decorrelating representations","year":"2015","author":"cogswell","key":"ref12"},{"key":"ref13","article-title":"Deep learning","volume":"1","author":"goodfellow","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/301"},{"article-title":"Generalized backpropagation,Étude de cas: Orthogonality","year":"2016","author":"harandi","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2832296"},{"article-title":"Improving neural networks by preventing co-adaptation of feature detectors","year":"2012","author":"hinton","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11768","article-title":"Orthogonal weight normalization: Solution to optimization over multiple dependent stiefel manifolds in deep neural networks","author":"huang","year":"2018","journal-title":"AAAI"},{"year":"0","key":"ref4"},{"year":"0","key":"ref3"},{"key":"ref6","first-page":"4261","article-title":"Can we gain more from orthogonality regularizations in training deep networks?","author":"bansal","year":"2018","journal-title":"NeurIPS"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref5"},{"key":"ref8","article-title":"Boosting occluded image classification via subspace decomposition-based estimation of deep features","author":"cen","year":"2019","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref7","first-page":"142","article-title":"Online learning and stochastic approximations","volume":"17","author":"bottou","year":"0","journal-title":"Online Learning in Neural Networks"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00348"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901376"},{"article-title":"Stochastic pooling for regular ization of deep convolutional neural networks","year":"2013","author":"zeiler","key":"ref46"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"zagoruyko","year":"2016"},{"key":"ref48","first-page":"1721","article-title":"Convergent block coordinate descent for training tikhonov regularized deep neural networks","author":"zhang","year":"2017","journal-title":"NeurIPS"},{"key":"ref47","first-page":"1286","article-title":"Hybrid orthogonal projection and estimation (hope): A new framework to learn neural networks","volume":"17","author":"zhang","year":"2016","journal-title":"JMLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2898777"},{"key":"ref44","article-title":"Regularization and learning an ensemble of rnns by decorrelating representations","author":"yadav","year":"2017","journal-title":"The AAAI-17 Workshop on Crowdsourcing Deep Learning and Artificial Intelligence Agents WS-17-07"},{"article-title":"Towards learning affine-invariant representations via data-efficient cnns","year":"2019","author":"xu","key":"ref43"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","start":{"date-parts":[[2020,3,1]]},"location":"Snowmass Village, CO, USA","end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093466.pdf?arnumber=9093466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T15:44:00Z","timestamp":1666539840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093466","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}