{"list":"other","total":58,"rows":[{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"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":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"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":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"1911.07053","title":"Maintaining Discrimination and Fairness in Class Incremental Learning","created":"2019-11-16","cited_by_count":283},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"2011.12945","title":"No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems","created":"2020-11-25","cited_by_count":209},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1508.03422","title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","created":"2015-08-14","cited_by_count":167},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"2006.07114","title":"Knowledge Distillation Meets Self-Supervision","created":"2020-06-12","cited_by_count":142},{"id":"2008.03673","title":"Feature Space Augmentation for Long-Tailed Data","created":"2020-08-09","cited_by_count":136},{"id":"1712.04440","title":"Data Distillation: Towards Omni-Supervised Learning","created":"2017-12-12","cited_by_count":126},{"id":"1709.01450","title":"The Devil is in the Tails: Fine-grained Classification in the Wild","created":"2017-09-05","cited_by_count":89},{"id":"1901.08665","title":"Fairness risk measures","created":"2019-01-24","cited_by_count":85},{"id":"2002.03532","title":"Understanding and Improving Knowledge Distillation","created":"2020-02-10","cited_by_count":83},{"id":"2006.05065","title":"Self-Distillation as Instance-Specific Label Smoothing","created":"2020-06-09","cited_by_count":71},{"id":"1811.00103","title":"The Price of Fair PCA: One Extra Dimension","created":"2018-10-31","cited_by_count":67},{"id":"1906.05082","title":"Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification","created":"2019-06-12","cited_by_count":60},{"id":"1912.01857","title":"Adjusting Decision Boundary for Class Imbalanced Learning","created":"2019-12-04","cited_by_count":52},{"id":"2010.14134","title":"Selective Classification Can Magnify Disparities Across Groups","created":"2020-10-27","cited_by_count":36},{"id":"2010.10090","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","created":"2020-10-20","cited_by_count":33},{"id":"2008.01458","title":"Prime-Aware Adaptive Distillation","created":"2020-08-04","cited_by_count":28},{"id":"1708.04106","title":"Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net","created":"2017-08-14","cited_by_count":27},{"id":"2104.05279","title":"Class-Balanced Distillation for Long-Tailed Visual Recognition","created":"2021-04-12","cited_by_count":27},{"id":"1606.08698","title":"Reviving Threshold-Moving: a Simple Plug-in Bagging Ensemble for Binary and Multiclass Imbalanced Data","created":"2016-06-28","cited_by_count":23},{"id":"2006.01683","title":"Channel Distillation: Channel-Wise Attention for Knowledge Distillation","created":"2020-06-02","cited_by_count":21},{"id":"2006.11979","title":"ELF: An Early-Exiting Framework for Long-Tailed Classification","created":"2020-06-22","cited_by_count":20},{"id":"1901.00366","title":"Learning Efficient Detector with Semi-supervised Adaptive Distillation","created":"2019-01-02","cited_by_count":10},{"id":"2004.03706","title":"Long-Tailed Recognition Using Class-Balanced Experts","created":"2020-04-07","cited_by_count":10},{"id":"1803.09014","title":"Feature Transfer Learning for Deep Face Recognition with Under-Represented Data","created":"2018-03-23","cited_by_count":4}],"next_cursor":null}