{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1803.02453","title":"A Reductions Approach to Fair Classification","created":"2018-03-06","cited_by_count":587},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"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":"1802.06309","title":"Learning Adversarially Fair and Transferable Representations","created":"2018-02-17","cited_by_count":353},{"id":"2104.14548","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","created":"2021-04-29","cited_by_count":326},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"id":"1412.4864","title":"Learning with Pseudo-Ensembles","created":"2014-12-16","cited_by_count":241},{"id":"1802.08626","title":"Empirical Risk Minimization under Fairness Constraints","created":"2018-02-23","cited_by_count":226},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"1906.02589","title":"Flexibly Fair Representation Learning by Disentanglement","created":"2019-06-06","cited_by_count":196},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"2004.10340","title":"The iWildCam 2020 Competition Dataset","created":"2020-04-21","cited_by_count":86},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80},{"id":"2011.04419","title":"Towards Domain-Agnostic Contrastive Learning","created":"2020-11-09","cited_by_count":75},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2105.07269","title":"Mean Shift for Self-Supervised Learning","created":"2021-05-15","cited_by_count":65},{"id":"2203.11819","title":"A Broad Study of Pre-training for Domain Generalization and Adaptation","created":"2022-03-22","cited_by_count":65},{"id":"1907.01439","title":"Operationalizing Individual Fairness with Pairwise Fair Representations","created":"2019-07-02","cited_by_count":64},{"id":"2106.05967","title":"Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations","created":"2021-06-10","cited_by_count":48},{"id":"2011.11779","title":"AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence","created":"2020-11-23","cited_by_count":22},{"id":"2008.05248","title":"Null-sampling for Interpretable and Fair Representations","created":"2020-08-12","cited_by_count":16},{"id":"2106.11853","title":"Credal Self-Supervised Learning","created":"2021-06-22","cited_by_count":15},{"id":"2208.02192","title":"RealPatch: A Statistical Matching Framework for Model Patching with Real Samples","created":"2022-08-03","cited_by_count":2}],"next_cursor":null}