{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"2006.01791","title":"SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization","created":"2020-06-02","cited_by_count":149},{"id":"1912.06798","title":"Cross-Batch Memory for Embedding Learning","created":"2019-12-14","cited_by_count":132},{"id":"2102.03065","title":"Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity","created":"2021-02-05","cited_by_count":128},{"id":"2001.04086","title":"GridMask Data Augmentation","created":"2020-01-13","cited_by_count":123},{"id":"2006.12000","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","created":"2020-06-22","cited_by_count":107},{"id":"1711.01575","title":"Adversarial Dropout Regularization","created":"2017-11-05","cited_by_count":106},{"id":"2011.12885","title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","created":"2020-11-25","cited_by_count":104},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79},{"id":"2002.11102","title":"On Feature Normalization and Data Augmentation","created":"2020-02-25","cited_by_count":71},{"id":"2103.06122","title":"Spatially Consistent Representation Learning","created":"2021-03-10","cited_by_count":64},{"id":"2003.05034","title":"SuperMix: Supervising the Mixing Data Augmentation","created":"2020-03-10","cited_by_count":58},{"id":"2012.04846","title":"SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data","created":"2020-12-09","cited_by_count":56},{"id":"1808.04699","title":"Improving Generalization via Scalable Neighborhood Component Analysis","created":"2018-08-14","cited_by_count":53},{"id":"2005.10389","title":"Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models","created":"2020-05-20","cited_by_count":50},{"id":"2108.10668","title":"Temporal Knowledge Consistency for Unsupervised Visual Representation Learning","created":"2021-08-24","cited_by_count":8}],"next_cursor":null}