Distribution Shift

A nonparametric method for gradual change problems with statistical guarantees NeurIPS 2021 AutoDO: Robust AutoAugment for Biased Data With Label Noise via Scalable Probabilistic Implicit Differentiation CVPR 2021 Coping with Label Shift via Distributionally Robust Optimisation ICLR 2021 DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature Distributions CVPR 2021 DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation AAAI 2021 Deep Stable Learning for Out-of-Distribution Generalization CVPR 2021 Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles NeurIPS 2021 Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition CVPR 2021 Does enforcing fairness mitigate biases caused by subpopulation shift? NeurIPS 2021 Don’t Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques EMNLP 2021 Empirical or Invariant Risk Minimization? A Sample Complexity Perspective ICLR 2021 Evaluating model performance under worst-case subpopulations NeurIPS 2021 Integrated Latent Heterogeneity and Invariance Learning in Kernel Space NeurIPS 2021 IRM—when it works and when it doesn't: A test case of natural language inference NeurIPS 2021 MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space CVPR 2021 ODIST: Open World Classification via Distributionally Shifted Instances EMNLP 2021 Overparameterization Improves Robustness to Covariate Shift in High Dimensions NeurIPS 2021 Recovering Latent Causal Factor for Generalization to Distributional Shifts NeurIPS 2021 Stable Adversarial Learning under Distributional Shifts AAAI 2021 Towards a Theoretical Framework of Out-of-Distribution Generalization NeurIPS 2021 A One-step Approach to Covariate Shift Adaptation ACML 2020 Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision CVPR 2020 Distributionally Robust Counterfactual Risk Minimization AAAI 2020 Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning NeurIPS 2020 Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets EMNLP 2020