{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"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":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"2104.09841","title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","created":"2021-04-20","cited_by_count":189},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"2007.02931","title":"Adaptive Risk Minimization: Learning to Adapt to Domain Shift","created":"2020-07-06","cited_by_count":183},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"1612.01939","title":"Correlation Alignment for Unsupervised Domain Adaptation","created":"2016-12-06","cited_by_count":147},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2009.00329","title":"Learning explanations that are hard to vary","created":"2020-09-01","cited_by_count":132},{"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":"2106.03721","title":"OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization","created":"2021-06-07","cited_by_count":86},{"id":"2202.06523","title":"MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts","created":"2022-02-14","cited_by_count":81},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51},{"id":"2106.02266","title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","created":"2021-06-04","cited_by_count":50},{"id":"2111.14341","title":"OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2021-11-29","cited_by_count":46},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41},{"id":"2106.03632","title":"Quantifying and Improving Transferability in Domain Generalization","created":"2021-06-07","cited_by_count":35},{"id":"2206.11646","title":"Invariant Causal Mechanisms through Distribution Matching","created":"2022-06-23","cited_by_count":31},{"id":"2206.08871","title":"How Robust is Unsupervised Representation Learning to Distribution Shift?","created":"2022-06-17","cited_by_count":24},{"id":"2110.09940","title":"Learning Representations that Support Robust Transfer of Predictors","created":"2021-10-19","cited_by_count":17},{"id":"2210.08748","title":"Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving","created":"2022-10-17","cited_by_count":2}],"next_cursor":null}