[AAAI2026] X-SAM: From Segment Anything to Any Segmentation

[npj Digital Medicine] The official repository for "Large-Vocabulary Segmentation for Medical Images with Text Prompts"

Pytorch implementation of convolutional neural network visualization techniques

[CVPR 2024 Oral] MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation.

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

🩺 首个会看胸部X光片的中文多模态医学大模型 | The first Chinese Medical Multimodal Model that Chest Radiographs Summarization.

RAGOnMedicalKG，将大模型RAG与KG结合，完成demo级问答，旨在给出基础的思路。

本项目设计了一个基于 RAG 与大模型技术的医疗问答系统，利用 DiseaseKG 数据集与 Neo4j 构 建知识图谱，结合 BERT 的命名实体识别和 34b 大模型的意图识别，通过精确的知识检索和问答生成， 提升系统在医疗咨询中的性能，解决大模型在医疗领域应用的可靠性问题。

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

PyTorch code and models for the DINOv2 self-supervised learning method.

Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything

Visualisation of VISOR Segmentations with Annotations and Relations

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Official implementation of the paper "Guided Distillation for Semi-Supervised Instance Segmentation".

Collection of AWESOME vision-language models for vision tasks

[CVPR 2024] Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective

OpenMMLab Computer Vision Foundation

DVIS: Decoupled Video Instance Segmentation Framework

A Collection of Variational Autoencoders (VAE) in PyTorch.

Awesome Multi-label Image Recognition Paper List

Segment Anything Model for Medical Image Segmentation: Open-Source Project Summary

DeepLab v3+ model in PyTorch. Support different backbones.

Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

This work is accepted by CVPR2023