FAIR adapts CLIP to unlabeled fine-grained domains by pseudo-labeling through a learned alignment score between localized image crops and learnable class anchors, claiming an average 2.78% top-1 gain over SOTA on 13 datasets.
Remote sens- ing image scene classification: Benchmark and state of the art
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
-
Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score
FAIR adapts CLIP to unlabeled fine-grained domains by pseudo-labeling through a learned alignment score between localized image crops and learnable class anchors, claiming an average 2.78% top-1 gain over SOTA on 13 datasets.