{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2010.04053","title":"Fairness in Machine Learning: A Survey","created":"2020-10-04","cited_by_count":370},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1806.08010","title":"Fairness Without Demographics in Repeated Loss Minimization","created":"2018-06-20","cited_by_count":364},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2010.06121","title":"To be Robust or to be Fair: Towards Fairness in Adversarial Training","created":"2020-10-13","cited_by_count":137},{"id":"2007.02561","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","created":"2020-07-06","cited_by_count":133},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117},{"id":"1910.02551","title":"Soft-Label Dataset Distillation and Text Dataset Distillation","created":"2019-10-06","cited_by_count":107},{"id":"1912.07768","title":"Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data","created":"2019-12-17","cited_by_count":104},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63},{"id":"2006.12621","title":"Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning","created":"2020-06-17","cited_by_count":56},{"id":"1907.04371","title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","created":"2019-07-09","cited_by_count":51},{"id":"2010.13365","title":"Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy","created":"2020-10-26","cited_by_count":45},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44},{"id":"1707.01047","title":"Robust Optimization for Non-Convex Objectives","created":"2017-07-04","cited_by_count":35},{"id":"2302.04025","title":"WAT: Improve the Worst-class Robustness in Adversarial Training","created":"2023-02-08","cited_by_count":27},{"id":"2309.14563","title":"Towards a statistical theory of data selection under weak supervision","created":"2023-09-25","cited_by_count":27},{"id":"2309.16748","title":"Discovering environments with XRM","created":"2023-09-28","cited_by_count":26},{"id":"2207.14499","title":"Class-Difficulty Based Methods for Long-Tailed Visual Recognition","created":"2022-07-29","cited_by_count":23},{"id":"2205.11672","title":"Why does Throwing Away Data Improve Worst-Group Error?","created":"2022-05-23","cited_by_count":22},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21},{"id":"2211.11109","title":"Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness","created":"2022-11-20","cited_by_count":21},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16},{"id":"2012.01604","title":"Going Beyond Classification Accuracy Metrics in Model Compression","created":"2020-12-03","cited_by_count":15},{"id":"2401.01867","title":"Dataset Difficulty and the Role of Inductive Bias","created":"2024-01-03","cited_by_count":12},{"id":"2302.06960","title":"Data pruning and neural scaling laws: fundamental limitations of score-based algorithms","created":"2023-02-14","cited_by_count":11},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9},{"id":"2309.06717","title":"Bias Amplification Enhances Minority Group Performance","created":"2023-09-13","cited_by_count":6},{"id":"2308.03821","title":"Distributionally Robust Classification on a Data Budget","created":"2023-08-07","cited_by_count":2}],"next_cursor":null}