Using CLIP image embeddings as retrieval keys and LLaVA as the answer generator, the paper reports 84% fish-classification accuracy on the FishNet dataset without domain-specific training.
An Image is Worth 16x16 Words: Transformers for Image Recogni- tion at Scale
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
-
Composing Open-domain Vision with RAG for Ocean Monitoring and Conservation
Using CLIP image embeddings as retrieval keys and LLaVA as the answer generator, the paper reports 84% fish-classification accuracy on the FishNet dataset without domain-specific training.