NoLA combines LLM class descriptions, DINO feature alignment, and visual prompt tuning to improve CLIP zero-shot classification without labels, averaging 3.6% over LaFTer on 11 datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections
NoLA combines LLM class descriptions, DINO feature alignment, and visual prompt tuning to improve CLIP zero-shot classification without labels, averaging 3.6% over LaFTer on 11 datasets.