Learning class-specific prompts on a frozen ViT yields attention maps that localize the discriminative traits used in fine-grained image classification.
Transformer inter- pretability beyond attention visualization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
Learning class-specific prompts on a frozen ViT yields attention maps that localize the discriminative traits used in fine-grained image classification.