[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

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

Graph Convolutional Networks in PyTorch

Official implementation of Character Region Awareness for Text Detection (CRAFT)

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

Corruption and Perturbation Robustness (ICLR 2019)

Large-Scale Visual Representation Model

Curate, Annotate, and Manage Your Data in LightlyStudio.

End-to-end learning of deep visual representations for image retrieval

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

PyTorch Implementation for Deep Metric Learning Pipelines

[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

Official code for CVPR 2022 paper "Rethinking Visual Geo-localization for Large-Scale Applications"

Official Implementation of "CAT-Seg🐱: Cost Aggregation for Open-Vocabulary Semantic Segmentation"

The code for the CVPR2019 paper Bi-Directional Cascade Network for Perceptual Edge Detection

ICCV 2023 Paper Global Features are All You Need for Image Retrieval and Reranking Official Repository

ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers

[ICML'24 Oral] "MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions"

Pytorch code of "Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning", CVPR 2019.

TLDR is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses

Metric learning models in PyTorch with results on CUB2011, CARS196, Stanford Online Products

Code for Recall@k Surrogate Loss with Large Batches and Similarity Mixup, CVPR 2022.

This repository contains the official implementation code of the NeurIPS 2025 paper: "Instance-Level Composed Image Retrieval".

A large-scale dataset for instance-level recognition for artworks is introduced.

AMES: Asymmetric and Memory-Efficient Similarity

Edge Augmentation for Large Scale Sketch Recognition without Sketches

Framework for computationally efficient training of universal image feature extraction models.

Implementation of [Understanding and Improving Kernel Local Descriptors](https://arxiv.org/abs/1811.11147) using PyTorch.