3 papers
cs.CV2026
Value-order Decomposition for Generalist Anomaly Detection
Miaoyun Zhao, Jing Chen, Miaoni Zhao +1
Industrial anomaly detection suffers from limited data, making cross-domain generalization particularly challenging. Generalist Anomaly Detection (GAD) aims to train a unified mode…
cs.CV2025
Fine-Grained Class-Conditional Distribution Balancing for Debiased Learning
Miaoyun Zhao, Qiang Zhang
Achieving group-robust generalization in the presence of spurious correlations remains a significant challenge, particularly when bias annotations are unavailable. Recent studies o…
cs.LG2025
Class-Conditional Distribution Balancing for Group Robust Classification
Miaoyun Zhao, Chenrong Li, Qiang Zhang
Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. Existing research attributes thi…