VEGA ranks pre-trained vision-language models for unlabeled datasets by measuring how well a model's own pseudo-labeled visual clusters align with class-name text features.
Clip-vg: Self-paced curriculum adapting of clip for visual grounding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks
VEGA ranks pre-trained vision-language models for unlabeled datasets by measuring how well a model's own pseudo-labeled visual clusters align with class-name text features.