image-retrieval

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Torchreid: Deep learning person re-identification in PyTorch.

Visual localization made easy with hloc

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video (ICML 2023)

[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features

[ICLR 2024] Official repository for "Vision-by-Language for Training-Free Compositional Image Retrieval"

source code and pre-trained/fine-tuned checkpoint for NAACL 2021 paper LightningDOT

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

A sample app for the Multimodal Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power Q&A experiences.

[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

YiShape Vector Database is a specialized vector database management system and application assistance system for new artificial intelligence applications such as large language models, natural language processing, and image retrieval.

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hosted). Full-corpus benchmarks vs FashionSigLIP, SigLIP-SO400M and ZooClaw — one harness, losses shown. #1 open model on LookBench.

Dataset and code for EMNLP 2022 "Visual Named Entity Linking: A New Dataset and A Baseline"

Grounding Language Models for Compositional and Spatial Reasoning

Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse