{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"2007.07936","title":"ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning","created":"2020-07-15","cited_by_count":209},{"id":"1604.04573","title":"CNN-RNN: A Unified Framework for Multi-label Image Classification","created":"2016-04-15","cited_by_count":190},{"id":"1409.2329","title":"Recurrent Neural Network Regularization","created":"2014-09-08","cited_by_count":189},{"id":"2006.01791","title":"SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization","created":"2020-06-02","cited_by_count":149},{"id":"2012.03236","title":"Cross-Layer Distillation with Semantic Calibration","created":"2020-12-06","cited_by_count":143},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128},{"id":"2011.14027","title":"General Multi-label Image Classification with Transformers","created":"2020-11-27","cited_by_count":127},{"id":"1908.07325","title":"Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition","created":"2019-08-20","cited_by_count":116},{"id":"2201.08371","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","created":"2022-01-20","cited_by_count":116},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"1702.05891","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","created":"2017-02-20","cited_by_count":85},{"id":"2106.09708","title":"Multi-Label Learning from Single Positive Labels","created":"2021-06-17","cited_by_count":81},{"id":"2012.02994","title":"Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition","created":"2020-12-05","cited_by_count":80},{"id":"1912.07872","title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","created":"2019-12-17","cited_by_count":79},{"id":"2012.11101","title":"ResizeMix: Mixing Data with Preserved Object Information and True Labels","created":"2020-12-21","cited_by_count":69},{"id":"2103.01795","title":"Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation","created":"2021-03-02","cited_by_count":69},{"id":"2004.00448","title":"Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy","created":"2020-04-01","cited_by_count":66},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52},{"id":"2007.01755","title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","created":"2020-07-03","cited_by_count":50},{"id":"2207.08409","title":"TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers","created":"2022-07-18","cited_by_count":48},{"id":"1712.07465","title":"Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition","created":"2017-12-20","cited_by_count":44},{"id":"2110.04722","title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","created":"2021-10-10","cited_by_count":41},{"id":"2112.10941","title":"Structured Semantic Transfer for Multi-Label Recognition with Partial Labels","created":"2021-12-21","cited_by_count":41},{"id":"2105.13343","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","created":"2021-05-27","cited_by_count":33},{"id":"2112.07368","title":"Simple and Robust Loss Design for Multi-Label Learning with Missing Labels","created":"2021-12-13","cited_by_count":30},{"id":"2108.09301","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","created":"2021-08-20","cited_by_count":27},{"id":"2012.12509","title":"Deep Semantic Dictionary Learning for Multi-label Image Classification","created":"2020-12-23","cited_by_count":20},{"id":"2203.06844","title":"RecursiveMix: Mixed Learning with History","created":"2022-03-14","cited_by_count":15},{"id":"2301.07236","title":"Effective End-to-End Vision Language Pretraining with Semantic Visual Loss","created":"2023-01-18","cited_by_count":10},{"id":"2211.12716","title":"Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision","created":"2022-11-23","cited_by_count":3},{"id":"2104.13582","title":"[Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2021-04-28","cited_by_count":1}],"next_cursor":null}