{"list":"other","total":71,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"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":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"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":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"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":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2010.01809","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","created":"2020-10-05","cited_by_count":271},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"2107.12028","title":"Parametric Contrastive Learning","created":"2021-07-26","cited_by_count":217},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210},{"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":"2003.10780","title":"Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective","created":"2020-03-24","cited_by_count":143},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100},{"id":"2101.10633","title":"ResLT: Residual Learning for Long-tailed Recognition","created":"2021-01-26","cited_by_count":96},{"id":"2107.09249","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","created":"2021-07-20","cited_by_count":95},{"id":"1901.07590","title":"Striking the Right Balance with Uncertainty","created":"2019-01-22","cited_by_count":79},{"id":"2001.01385","title":"Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning","created":"2020-01-06","cited_by_count":76},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74},{"id":"2109.03216","title":"Learning Fast Sample Re-weighting Without Reward Data","created":"2021-09-07","cited_by_count":69},{"id":"2106.09859","title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","created":"2021-06-18","cited_by_count":61},{"id":"2309.10019","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","created":"2023-09-18","cited_by_count":58},{"id":"1607.01097","title":"AdaNet: Adaptive Structural Learning of Artificial Neural Networks","created":"2016-07-05","cited_by_count":54},{"id":"2010.11820","title":"Posterior Re-calibration for Imbalanced Datasets","created":"2020-10-22","cited_by_count":53},{"id":"1705.08826","title":"Learning with Average Top-k Loss","created":"2017-05-24","cited_by_count":52},{"id":"1912.01857","title":"Adjusting Decision Boundary for Class Imbalanced Learning","created":"2019-12-04","cited_by_count":52},{"id":"2104.09658","title":"Calibration and Consistency of Adversarial Surrogate Losses","created":"2021-04-19","cited_by_count":47},{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38},{"id":"2310.14772","title":"Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms","created":"2023-10-23","cited_by_count":36},{"id":"2310.18236","title":"How Re-sampling Helps for Long-Tail Learning?","created":"2023-10-27","cited_by_count":36},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32},{"id":"2310.14770","title":"Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention","created":"2023-10-23","cited_by_count":32},{"id":"2302.02334","title":"Revisiting Discriminative vs. Generative Classifiers: Theory and Implications","created":"2023-02-05","cited_by_count":29},{"id":"2403.19494","title":"Regression with Multi-Expert Deferral","created":"2024-03-28","cited_by_count":29},{"id":"2307.02035","title":"Ranking with Abstention","created":"2023-07-05","cited_by_count":27},{"id":"2105.01550","title":"A Finer Calibration Analysis for Adversarial Robustness","created":"2021-05-04","cited_by_count":26},{"id":"2407.13732","title":"Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer","created":"2024-07-18","cited_by_count":26},{"id":"2310.04752","title":"A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization","created":"2023-10-07","cited_by_count":24},{"id":"2405.05968","title":"A Universal Growth Rate for Learning with Smooth Surrogate Losses","created":"2024-05-09","cited_by_count":24},{"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":"2407.07140","title":"Cardinality-Aware Set Prediction and Top-$k$ Classification","created":"2024-07-09","cited_by_count":23},{"id":"2407.13746","title":"Multi-Label Learning with Stronger Consistency Guarantees","created":"2024-07-18","cited_by_count":22},{"id":"2206.08704","title":"Maximum Class Separation as Inductive Bias in One Matrix","created":"2022-06-17","cited_by_count":21},{"id":"2403.19480","title":"$H$-Consistency Guarantees for Regression","created":"2024-03-28","cited_by_count":21},{"id":"1605.06443","title":"Structured Prediction Theory Based on Factor Graph Complexity","created":"2016-05-20","cited_by_count":18},{"id":"1804.02246","title":"Adaptive Cost-sensitive Online Classification","created":"2018-04-06","cited_by_count":18},{"id":"2407.13722","title":"Enhanced $H$-Consistency Bounds","created":"2024-07-18","cited_by_count":18},{"id":"2310.07587","title":"Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer","created":"2023-10-11","cited_by_count":17},{"id":"2410.15729","title":"A Two-Stage Learning-to-Defer Approach for Multi-Task Learning","created":"2024-10-21","cited_by_count":17},{"id":"2305.01160","title":"Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels","created":"2023-05-02","cited_by_count":16},{"id":"2502.01027","title":"Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees","created":"2025-02-03","cited_by_count":16},{"id":"2405.07780","title":"DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations","created":"2024-05-13","cited_by_count":15},{"id":"2410.15761","title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","created":"2024-10-21","cited_by_count":15},{"id":"2402.13505","title":"SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning","created":"2024-02-21","cited_by_count":14},{"id":"2405.09782","title":"Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection","created":"2024-05-16","cited_by_count":14},{"id":"2305.18732","title":"Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition","created":"2023-05-30","cited_by_count":11},{"id":"2310.12152","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","created":"2023-10-18","cited_by_count":11},{"id":"1911.07498","title":"Online Adaptive Asymmetric Active Learning with Limited Budgets","created":"2019-11-18","cited_by_count":10},{"id":"2406.02435","title":"Generative Active Learning for Long-tailed Instance Segmentation","created":"2024-06-04","cited_by_count":10},{"id":"2405.09535","title":"Restoring balance: principled under/oversampling of data for optimal classification","created":"2024-05-15","cited_by_count":6}],"next_cursor":null}