AIBullisharXiv – CS AI · 10h ago6/10
🧠
CAMAL: Improving Attention Alignment and Faithfulness with Segmentation Masks
Researchers introduce CAMAL, a method that leverages segmentation masks to improve attention alignment and faithfulness in vision models across deep learning and reinforcement learning paradigms. The approach achieves over 35% improvements in attention faithfulness while maintaining or improving generalization performance without additional inference costs.