Random crops plus an optimal-transport match between image patches and LLM-generated class descriptions lets CLIP use fine-grained local details and improves zero-shot, few-shot, and test-time classification.
Visual classification via description from large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach
Random crops plus an optimal-transport match between image patches and LLM-generated class descriptions lets CLIP use fine-grained local details and improves zero-shot, few-shot, and test-time classification.