{"list":"other","total":53,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"id":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"2010.01809","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","created":"2020-10-05","cited_by_count":271},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"2107.12028","title":"Parametric Contrastive Learning","created":"2021-07-26","cited_by_count":217},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"2001.01536","title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","created":"2020-01-06","cited_by_count":175},{"id":"2012.00321","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","created":"2020-12-01","cited_by_count":172},{"id":"1508.03422","title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","created":"2015-08-14","cited_by_count":167},{"id":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2207.09052","title":"Balanced Contrastive Learning for Long-Tailed Visual Recognition","created":"2022-07-19","cited_by_count":144},{"id":"2004.00431","title":"M2m: Imbalanced Classification via Major-to-minor Translation","created":"2020-04-01","cited_by_count":134},{"id":"2007.11978","title":"The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation","created":"2020-07-23","cited_by_count":108},{"id":"2203.14197","title":"Long-Tailed Recognition via Weight Balancing","created":"2022-03-27","cited_by_count":107},{"id":"2112.00412","title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","created":"2021-12-01","cited_by_count":100},{"id":"2103.12579","title":"MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition","created":"2021-03-23","cited_by_count":99},{"id":"2101.10633","title":"ResLT: Residual Learning for Long-tailed Recognition","created":"2021-01-26","cited_by_count":96},{"id":"2110.02444","title":"Influence-Balanced Loss for Imbalanced Visual Classification","created":"2021-10-06","cited_by_count":91},{"id":"2108.02385","title":"ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot","created":"2021-08-05","cited_by_count":86},{"id":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76},{"id":"2109.04075","title":"Self Supervision to Distillation for Long-Tailed Visual Recognition","created":"2021-09-09","cited_by_count":73},{"id":"2203.15359","title":"Nested Collaborative Learning for Long-Tailed Visual Recognition","created":"2022-03-29","cited_by_count":63},{"id":"2106.09859","title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","created":"2021-06-18","cited_by_count":61},{"id":"2111.09030","title":"Trustworthy Long-Tailed Classification","created":"2021-11-17","cited_by_count":51},{"id":"2203.01522","title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","created":"2022-03-03","cited_by_count":29}],"next_cursor":null}