Latest

• LEMoN: Label Error Detection using Multimodal Neighbors
• Test-Time Debiasing of Vision-Language Embeddings
• The limits of fair medical imaging AI in real-world generalization
• Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
• Algorithmic Fairness in Chest X-ray Diagnosis: A Case Study
• Change is Hard: A Closer Look at Subpopulation Shift
• A comparison of approaches to improve worst-case predictive model performance over patient subpopulations
• Improving the Fairness of Chest X-ray Classifiers
• The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
• An empirical framework for domain generalization in clinical settings
• Learning Optimal Predictive Checklists
• Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
• Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations
• An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
• Hurtful words: quantifying biases in clinical contextual word embeddings
• Self-supervised contrastive learning of protein representations by mutual information maximization