{"list":"other","total":67,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"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":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1508.07680","title":"Domain Generalization for Object Recognition with Multi-task Autoencoders","created":"2015-08-31","cited_by_count":253},{"id":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"1901.08846","title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","created":"2019-01-25","cited_by_count":213},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","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":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"id":"1911.07661","title":"Domain Generalization Using a Mixture of Multiple Latent Domains","created":"2019-11-18","cited_by_count":170},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134},{"id":"2007.02561","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","created":"2020-07-06","cited_by_count":133},{"id":"2009.00329","title":"Learning explanations that are hard to vary","created":"2020-09-01","cited_by_count":132},{"id":"1908.02729","title":"Robust Learning with Jacobian Regularization","created":"2019-08-07","cited_by_count":129},{"id":"2008.12839","title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","created":"2020-08-28","cited_by_count":128},{"id":"2006.12433","title":"What shapes feature representations? Exploring datasets, architectures, and training","created":"2020-06-22","cited_by_count":126},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"1812.02224","title":"Adapting Auxiliary Losses Using Gradient Similarity","created":"2018-12-05","cited_by_count":100},{"id":"1905.01298","title":"SCOPS: Self-Supervised Co-Part Segmentation","created":"2019-05-03","cited_by_count":100},{"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":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"1605.08179","title":"Discovering Causal Signals in Images","created":"2016-05-26","cited_by_count":79},{"id":"2006.12107","title":"Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series","created":"2020-06-22","cited_by_count":77},{"id":"2005.09241","title":"On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law","created":"2020-05-19","cited_by_count":74},{"id":"1901.09981","title":"Improving Adversarial Robustness of Ensembles with Diversity Training","created":"2019-01-28","cited_by_count":69},{"id":"2004.09034","title":"Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision","created":"2020-04-20","cited_by_count":66},{"id":"1706.08058","title":"Invariant Causal Prediction for Sequential Data","created":"2017-06-25","cited_by_count":63},{"id":"1809.10966","title":"Domain Generalization with Domain-Specific Aggregation Modules","created":"2018-09-28","cited_by_count":61},{"id":"2006.12621","title":"Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning","created":"2020-06-17","cited_by_count":56},{"id":"1901.11058","title":"HyperGAN: A Generative Model for Diverse, Performant Neural Networks","created":"2019-01-30","cited_by_count":51},{"id":"2012.09382","title":"DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation","created":"2020-12-17","cited_by_count":48},{"id":"2011.03856","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","created":"2020-11-07","cited_by_count":43},{"id":"1511.05077","title":"Diversity Networks: Neural Network Compression Using Determinantal Point Processes","created":"2015-11-16","cited_by_count":25},{"id":"2004.02709","title":"Evaluating Models' Local Decision Boundaries via Contrast Sets","created":"2020-04-06","cited_by_count":24},{"id":"1911.01291","title":"Ensembles of Locally Independent Prediction Models","created":"2019-11-04","cited_by_count":22},{"id":"1712.04006","title":"Training Ensembles to Detect Adversarial Examples","created":"2017-12-11","cited_by_count":10},{"id":"1806.08716","title":"Learning Qualitatively Diverse and Interpretable Rules for Classification","created":"2018-06-22","cited_by_count":10},{"id":"2104.14372","title":"A neural anisotropic view of underspecification in deep learning","created":"2021-04-29","cited_by_count":6},{"id":"1511.07110","title":"On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization","created":"2015-11-23","cited_by_count":4},{"id":"2003.13866","title":"Dataless Model Selection with the Deep Frame Potential","created":"2020-03-30","cited_by_count":4},{"id":"1511.09033","title":"The Multiverse Loss for Robust Transfer Learning","created":"2015-11-29","cited_by_count":2},{"id":"2006.07119","title":"Learning Diverse Representations for Fast Adaptation to Distribution Shift","created":"2020-06-12","cited_by_count":2}],"next_cursor":null}