AIBullisharXiv – CS AI · Mar 36/106
🧠
What Helps -- and What Hurts: Bidirectional Explanations for Vision Transformers
Researchers propose BiCAM, a new method for interpreting Vision Transformer (ViT) decisions that captures both positive and negative contributions to predictions. The approach improves explanation quality and enables adversarial example detection across multiple ViT variants without requiring model retraining.