Can I read ELIP: Enhancing Image Retrieval Models on EtoBox?

ELIP: Enhancing Image Retrieval Models by VINOTH R is a document available to read on EtoBox.

What is ELIP: Enhancing Image Retrieval Models about?

The document presents ELIP, a novel framework designed to enhance text-to-image retrieval performance by improving existing vision-language models like CLIP, SigLIP, and BLIP-2. ELIP utilizes a lightweight architecture that incorporates text-guided visual prompts to refine image embeddings, leading to improved re-ranking outcomes. The authors demonstrate that their approach significantly outperforms state-of-the-art models on standard and new out-of-distribution benchmarks.

Author

VINOTH R

Language

EN