Optimizing Relevance Maps of Vision Transformers Improves Robustness
Cited by 2
Related Papers
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
|ACM Transactions on Graphics|2023|384
Lumiere: A Space-Time Diffusion Model for Video Generation
|Unknown|2024|120
Transformer Interpretability Beyond Attention Visualization
|Unknown|2021|44
Image-Based CLIP-Guided Essence Transfer
|Lecture notes in computer science|2022|34
No Token Left Behind: Explainability-Aided Image Classification and Generation
|Lecture notes in computer science|2022|22