APL improves fine-grained Generalized Category Discovery by learning shared, correspondable object-part features with an all-min contrastive loss, replacing the CLS token and gaining 2 to 6 accuracy points over SimGCD, SPTNet, and CMS.
k-means++: The advantages of careful seeding
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
-
Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
APL improves fine-grained Generalized Category Discovery by learning shared, correspondable object-part features with an all-min contrastive loss, replacing the CLS token and gaining 2 to 6 accuracy points over SimGCD, SPTNet, and CMS.