{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"1806.08010","title":"Fairness Without Demographics in Repeated Loss Minimization","created":"2018-06-20","cited_by_count":364},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"2006.13114","title":"Fairness without Demographics through Adversarially Reweighted Learning","created":"2020-06-23","cited_by_count":251},{"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":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"2007.02561","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","created":"2020-07-06","cited_by_count":133},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"1903.06256","title":"Learning Robust Representations by Projecting Superficial Statistics Out","created":"2019-03-02","cited_by_count":123},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105},{"id":"2105.03818","title":"Heterogeneous Risk Minimization","created":"2021-05-09","cited_by_count":90},{"id":"2005.00315","title":"Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance","created":"2020-05-01","cited_by_count":85},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"2306.11074","title":"Simple and Fast Group Robustness by Automatic Feature Reweighting","created":"2023-06-19","cited_by_count":68},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2206.10843","title":"Learning Debiased Classifier with Biased Committee","created":"2022-06-22","cited_by_count":51},{"id":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47},{"id":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39},{"id":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35},{"id":"2203.15516","title":"Rich Feature Construction for the Optimization-Generalization Dilemma","created":"2022-03-24","cited_by_count":34},{"id":"2005.06251","title":"Mitigating Gender Bias Amplification in Distribution by Posterior Regularization","created":"2020-05-13","cited_by_count":27},{"id":"2302.00457","title":"Simplicity Bias in 1-Hidden Layer Neural Networks","created":"2023-02-01","cited_by_count":26},{"id":"2201.00072","title":"BARACK: Partially Supervised Group Robustness With Guarantees","created":"2021-12-31","cited_by_count":25},{"id":"2205.14594","title":"Revisiting the Importance of Amplifying Bias for Debiasing","created":"2022-05-29","cited_by_count":19},{"id":"2211.15231","title":"Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers","created":"2022-11-28","cited_by_count":17},{"id":"2105.12628","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","created":"2021-05-26","cited_by_count":16},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12},{"id":"2302.02931","title":"Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts","created":"2023-02-06","cited_by_count":9},{"id":"2210.05248","title":"Self-supervised debiasing using low rank regularization","created":"2022-10-11","cited_by_count":8},{"id":"2108.11056","title":"Social Norm Bias: Residual Harms of Fairness-Aware Algorithms","created":"2021-08-25","cited_by_count":6},{"id":"2204.12941","title":"Unsupervised Learning of Unbiased Visual Representations","created":"2022-04-26","cited_by_count":2}],"next_cursor":null}