Pytorch implement of the paper "VLDeformer: Vision Language Decomposed Transformer for Fast Cross-modal Retrieval", KBS 2022
-
Updated
Sep 18, 2022 - Jupyter Notebook
Pytorch implement of the paper "VLDeformer: Vision Language Decomposed Transformer for Fast Cross-modal Retrieval", KBS 2022
Text to image search & Image Similarity Search using @typesense
SnapSort is a cross-platform desktop application for offline, face-based image sorting and viewing.
OpenAI's CLIP neural network
Your all-local photo organizer and photo search tool
CLIPIndia 🇮🇳👗 adapts SigLIP for Indian fashion using parameter-efficient contrastive fine-tuning. It enables text, image, and compositional image+text search. Results: +57.7% Recall@1 on regional apparel, <2% degradation on general retrieval, trained efficiently on a single GPU.
To associate your repository with the text-to-image-search topic, visit your repo's landing page and select "manage topics."