distribution shift

CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization EMNLP 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 and Adapting to Irregular Distribution Shifts in Bayesian Online Learning NeurIPS 2021 Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles NeurIPS 2021 Detoxifying Language Models Risks Marginalizing Minority Voices NAACL 2021 Empirical or Invariant Risk Minimization? A Sample Complexity Perspective ICLR 2021 Encoding Robustness to Image Style via Adversarial Feature Perturbations NeurIPS 2021 Environment Inference for Invariant Learning ICML 2021 Evaluating Model Robustness and Stability to Dataset Shift AISTATS 2021 Examining and Combating Spurious Features under Distribution Shift ICML 2021 How to Learn when Data Reacts to Your Model: Performative Gradient Descent ICML 2021 Identifying and Benchmarking Natural Out-of-Context Prediction Problems NeurIPS 2021 Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction NeurIPS 2021 In Search of Lost Domain Generalization ICLR 2021 Instabilities of Offline RL with Pre-Trained Neural Representation ICML 2021 Introspective Distillation for Robust Question Answering NeurIPS 2021 IRM—when it works and when it doesn't: A test case of natural language inference NeurIPS 2021 Learning from Biased Data: A Semi-Parametric Approach ICML 2021 Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation CVPR 2021 Learning Prediction Intervals for Model Performance AAAI 2021 Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021 Mandoline: Model Evaluation under Distribution Shift ICML 2021 Minimax Model Learning AISTATS 2021 MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space CVPR 2021