A CLIP teacher with quality-grade prompts distills knowledge into lightweight student encoders via cosine-annealed soft and hard label losses, reporting SOTA IQA scores at 5-28M parameters.
Exploring clip for assessing the look and feel of images,
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
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Visual-Language Model Knowledge Distillation Method for Image Quality Assessment
A CLIP teacher with quality-grade prompts distills knowledge into lightweight student encoders via cosine-annealed soft and hard label losses, reporting SOTA IQA scores at 5-28M parameters.