SCPT encodes pairwise class relationships via signed random projection and applies SVD-based semantic denoising to improve CLIP prompt tuning for fine-grained image recognition.
Convolution-enhanced bi-branch adaptive transformer with cross-task interaction for food category and ingredient recognition
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
-
Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition
SCPT encodes pairwise class relationships via signed random projection and applies SVD-based semantic denoising to improve CLIP prompt tuning for fine-grained image recognition.