Synthetic images from text captions, combined with a shared prompt-adapter, improve multi-label image recognition and reduce CLIP's modality gap.
Learning semantic-specific graph representation for multi-label image recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning
Synthetic images from text captions, combined with a shared prompt-adapter, improve multi-label image recognition and reduce CLIP's modality gap.