{"list":"other","total":100,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"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":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"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":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"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":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"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":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1610.07524","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","created":"2016-10-24","cited_by_count":672},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1803.02453","title":"A Reductions Approach to Fair Classification","created":"2018-03-06","cited_by_count":587},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"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":"1807.00431","title":"Confounding variables can degrade generalization performance of radiological deep learning models","created":"2018-07-02","cited_by_count":379},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"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":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"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":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"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":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"1608.08614","title":"What makes ImageNet good for transfer learning?","created":"2016-08-30","cited_by_count":192},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"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":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"1811.11553","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","created":"2018-11-28","cited_by_count":143},{"id":"1909.02060","title":"Distributionally Robust Language Modeling","created":"2019-09-04","cited_by_count":143},{"id":"2006.12433","title":"What shapes feature representations? Exploring datasets, architectures, and training","created":"2020-06-22","cited_by_count":126},{"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":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"id":"2204.02070","title":"Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation","created":"2022-04-05","cited_by_count":88},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86},{"id":"1408.6491","title":"Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination","created":"2014-08-27","cited_by_count":83},{"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":"2106.00545","title":"Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests","created":"2021-05-31","cited_by_count":77},{"id":"2010.12230","title":"Coping with Label Shift via Distributionally Robust Optimisation","created":"2020-10-23","cited_by_count":70},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69},{"id":"1811.00401","title":"Excessive Invariance Causes Adversarial Vulnerability","created":"2018-11-01","cited_by_count":66},{"id":"2010.02114","title":"Explaining The Efficacy of Counterfactually Augmented Data","created":"2020-10-05","cited_by_count":65},{"id":"2110.03095","title":"Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective","created":"2021-10-06","cited_by_count":57},{"id":"2012.01750","title":"Understanding Failures of Deep Networks via Robust Feature Extraction","created":"2020-12-03","cited_by_count":56},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51},{"id":"1812.06707","title":"Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation","created":"2018-12-17","cited_by_count":49},{"id":"2006.15766","title":"Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization","created":"2020-06-29","cited_by_count":49},{"id":"1611.02041","title":"Does Distributionally Robust Supervised Learning Give Robust Classifiers?","created":"2016-11-07","cited_by_count":38},{"id":"2002.11894","title":"Unshuffling Data for Improved Generalization","created":"2020-02-27","cited_by_count":35},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32},{"id":"2108.05449","title":"Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization","created":"2021-08-11","cited_by_count":32},{"id":"2102.10867","title":"Linear unit-tests for invariance discovery","created":"2021-02-22","cited_by_count":27},{"id":"2201.00072","title":"BARACK: Partially Supervised Group Robustness With Guarantees","created":"2021-12-31","cited_by_count":25},{"id":"2006.06865","title":"Exploring Algorithmic Fairness in Robust Graph Covering Problems","created":"2020-06-11","cited_by_count":19},{"id":"2201.11259","title":"Controlling Directions Orthogonal to a Classifier","created":"2022-01-27","cited_by_count":13},{"id":"1605.05538","title":"Improving Weakly-Supervised Object Localization By Micro-Annotation","created":"2016-05-18","cited_by_count":11},{"id":"1906.03518","title":"Maximum Weighted Loss Discrepancy","created":"2019-06-08","cited_by_count":11}],"next_cursor":null}