official repo for ArtiLatent (siggraph asia 2025)

Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes

[IEEE SENSORS 2025] PicoSAM2 is a minimal, prompt-based segmentation model distilled from Meta’s SAM 2.1

Vision Foundation Models for Medical AI, including RETFound, DINOv2, DINOv3

Official code for "No time to train! Training-Free Reference-Based Instance Segmentation"

A summarization of Few-shot Learning approaches for Computer Vision tasks, including image classification, object detection, and object segmentation. Keep updated frequently.

From 2018 to 2022

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

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

Awesome Active Domain Adaptation for Medical Image Analysis

[ICCV2025] Harnessing CLIP, DINO and SAM for Open Vocabulary Segmentation

Reference PyTorch implementation and models for DINOv3

Fully automated estimation of glomerular basement membrane thickness via active semi-supervised learning model

Official repository of "Heterogeneous Feature Mutual-Calibration Assisted Online Distillation for Efficient Face Anti-Spoofing"

Semi-supervised Medical Image Segmentation through Dual-task Consistency

This repository is for the first survey on SAM & SAM2 for Videos.

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

Exploration of CNN-, ViT-, Mamba-, and KAN-based UNet for Medical Image Segmentation.

The official implementation of the paper "Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation".

【ACCVW2025 Oral】Offical Pytorch Code for "SkinMamba: A Precision Skin Lesion Segmentation Architecture with Cross-Scale Global State Modeling and Frequency Boundary Guidance"

Code for Pseudo label based contrastive learning joint training approach

[TPAMI 2025] Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection

[CVPR 2025] MINIMA: Modality Invariant Image Matching

Official implementation for the paper"Towards Understanding How Knowledge Evolves in Large Vision-Language Models"

SAFIRE: Segment Any Forged Image REgion (AAAI 2025). Official Repo.

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more