conftrace_

spurious correlation

344 papers

Explore in graph

Co-occurring keywords · papers mentioning both

causal inference (66) domain generalization (64) out-of-distribution generalization (45) representation learning (26) bias mitigation (23) shortcut learning (21) empirical risk minimization (20) worst-group accuracy (19) text classification (19) contrastive learning (19)

Papers

Self-supervised Debiasing Using Low Rank Regularization CVPR 2024 Targeted Activation Penalties Help CNNs Ignore Spurious Signals AAAI 2024 TFCD: Towards Multi-modal Sarcasm Detection via Training-Free Counterfactual Debiasing IJCAI 2024 The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations NeurIPS 2024 The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing NeurIPS 2024 The Instinctive Bias: Spurious Images lead to Illusion in MLLMs EMNLP 2024 Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models EACL 2024 Towards Reliable Learning in the Wild: Generalization and Adaptation AAAI 2024 Trend-Aware Supervision: On Learning Invariance for Semi-supervised Facial Action Unit Intensity Estimation AAAI 2024 Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution AAAI 2024 Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis EACL 2024 Understanding Domain Generalization: A Noise Robustness Perspective ICLR 2024 Unraveling the Key Components of OOD Generalization via Diversification ICLR 2024 Unsupervised Concept Discovery Mitigates Spurious Correlations ICML 2024 Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation ICLR 2024 Vision-and-Language Navigation via Causal Learning CVPR 2024 Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations ICML 2023 AGRO: Adversarial discovery of error-prone Groups for Robust Optimization ICLR 2023 Avoiding spurious correlations via logit correction ICLR 2023 A Whac-a-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others CVPR 2023 Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification ICCV 2023 Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations NeurIPS 2023 BiasAdv: Bias-Adversarial Augmentation for Model Debiasing CVPR 2023 Bias Mimicking: A Simple Sampling Approach for Bias Mitigation CVPR 2023 Causal Balancing for Domain Generalization ICLR 2023