Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning

2026-02-13

AI Summary

This work addresses the challenge of label scarcity in clinical chest X-ray classification, characterized by a long-tailed distribution of disease labels and missing annotations for rare or previously unseen diseases. It presents the first unified framework that jointly tackles long-tailed multi-label classification and zero-shot recognition of unknown diseases. The approach incorporates an imbalance-aware learning strategy to enhance performance on tail classes and introduces an unsupervised zero-shot prediction method that requires no out-of-distribution (OOD) annotations, leveraging semantic or feature-level transfer to infer scores for unseen diseases. Optimized with macro-averaged mAP as the objective, the proposed model achieved top rankings in both tasks during the development phase of the CXR-LT 2026 Challenge, significantly outperforming existing methods.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Segmentation
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Chest X-ray (CXR) classification in clinical practice is often limited by imperfect supervision, arising from (i) extreme long-tailed multi-label disease distributions and (ii) missing annotations for rare or previously unseen findings. The CXR-LT 2026 challenge addresses these issues on a PadChest-based benchmark with a 36-class label space split into 30 in-distribution classes for training and 6 out-of-distribution (OOD) classes for zero-shot evaluation. We present task-specific solutions tailored to the distinct supervision regimes. For Task 1 (long-tailed multi-label classification), we adopt an imbalance-aware multi-label learning strategy to improve recognition of tail classes while maintaining stable performance on frequent findings. For Task 2 (zero-shot OOD recognition), we propose a prediction approach that produces scores for unseen disease categories without using any supervised labels or examples from the OOD classes during training. Evaluated with macro-averaged mean Average Precision (mAP), our method achieves strong performance on both tasks, ranking first on the public leaderboard of the development phase. Code and pre-trained models are available at https://github.com/hieuphamha19/CXR_LT.

Problem

• supervision scarcity
• chest X-ray classification
• long-tailed learning
• zero-shot learning
• out-of-distribution detection

Innovation

• long-tailed learning
• zero-shot learning
• chest X-ray classification
• out-of-distribution detection
• multi-label imbalance