Sep 2026
Cross-Modality Causal-Aware Hierarchical Representation Learning for Domain Generalized Object Detection.
A Causal-aware Hierarchical Representation Graph is developed that reformulates the VLM-based DG problem into a hierarchical causal representation learning framework and provides a vision-friendly perspective for leveraging VLMs to solve vision-centric tasks.
Ya-Jing Liu, Zhi-Yuan Liu, Xi-Yao Liu et al.
· IEEE Transactions on Pattern... · 0 citations