Random-crop regions scored by CLIP pseudo-label soft negative margin outperform SAM-mask regions for label-free fine-grained classification.
Valse: A task-independent benchmark for vision and language models centered on linguistic phenomena
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification
Random-crop regions scored by CLIP pseudo-label soft negative margin outperform SAM-mask regions for label-free fine-grained classification.