{"list":"other","total":58,"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"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":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"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":"1806.08010","title":"Fairness Without Demographics in Repeated Loss Minimization","created":"2018-06-20","cited_by_count":364},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"1812.03372","title":"What is the Effect of Importance Weighting in Deep Learning?","created":"2018-12-08","cited_by_count":251},{"id":"2006.13114","title":"Fairness without Demographics through Adversarially Reweighted Learning","created":"2020-06-23","cited_by_count":251},{"id":"1912.01805","title":"Adversarial Domain Adaptation with Domain Mixup","created":"2019-12-04","cited_by_count":250},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"2010.04819","title":"How Does Mixup Help With Robustness and Generalization?","created":"2020-10-09","cited_by_count":193},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2204.11423","title":"Trusted Multi-View Classification with Dynamic Evidential Fusion","created":"2022-04-25","cited_by_count":168},{"id":"1805.08206","title":"Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers","created":"2018-05-21","cited_by_count":113},{"id":"2007.01458","title":"Confidence-Aware Learning for Deep Neural Networks","created":"2020-07-03","cited_by_count":113},{"id":"2001.02394","title":"Convolutional Networks with Dense Connectivity","created":"2020-01-08","cited_by_count":98},{"id":"2006.06049","title":"On Mixup Regularization","created":"2020-06-10","cited_by_count":83},{"id":"2006.08437","title":"Depth Uncertainty in Neural Networks","created":"2020-06-15","cited_by_count":57},{"id":"2210.05775","title":"C-Mixup: Improving Generalization in Regression","created":"2022-10-11","cited_by_count":57},{"id":"2106.06142","title":"DORO: Distributional and Outlier Robust Optimization","created":"2021-06-11","cited_by_count":56},{"id":"2103.15209","title":"Understanding the role of importance weighting for deep learning","created":"2021-03-28","cited_by_count":39},{"id":"2111.08456","title":"Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions","created":"2021-11-11","cited_by_count":39},{"id":"1611.02041","title":"Does Distributionally Robust Supervised Learning Give Robust Classifiers?","created":"2016-11-07","cited_by_count":38},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34},{"id":"2209.08928","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","created":"2022-09-19","cited_by_count":34},{"id":"2103.10282","title":"Modeling the Second Player in Distributionally Robust Optimization","created":"2021-03-18","cited_by_count":29},{"id":"2201.05776","title":"Uncertainty-Aware Multi-View Representation Learning","created":"2022-01-15","cited_by_count":29},{"id":"2201.12293","title":"Understanding Why Generalized Reweighting Does Not Improve Over ERM","created":"2022-01-28","cited_by_count":29},{"id":"2003.03397","title":"Dropout: Explicit Forms and Capacity Control","created":"2020-03-06","cited_by_count":27},{"id":"2208.09913","title":"A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective","created":"2022-08-21","cited_by_count":27},{"id":"2110.02619","title":"Focus on the Common Good: Group Distributional Robustness Follows","created":"2021-10-06","cited_by_count":25},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24},{"id":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21},{"id":"2204.06340","title":"Distributionally Robust Models with Parametric Likelihood Ratios","created":"2022-04-13","cited_by_count":17},{"id":"2110.13948","title":"Boosted CVaR Classification","created":"2021-10-26","cited_by_count":12}],"next_cursor":null}