A weakly supervised segmentation method uses class-specific CLS tokens and random token masking to turn ViT attention maps into pseudo-masks.
Emerg- ing properties in self-supervised vision transformers
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
background 1representative citing papers
citing papers explorer
-
Know Your Attention Maps: Class-specific Token Masking for Weakly Supervised Semantic Segmentation
A weakly supervised segmentation method uses class-specific CLS tokens and random token masking to turn ViT attention maps into pseudo-masks.