Official code of SmartEdit [CVPR-2024 Highlight]

Official repository for the paper "FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentation".

One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesis (pFLSynth)

A comprehensive review of techniques to address the missing-modality problem for medical images

vessel segmentation, artery and vein, optic disc, vascular feature analysis

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

A novel segmentation model termed Swin UNEt TRansformers (Swin UNETR). Specially for the task of 3D semantic segmentation.

Code base for the precision, recall, density, and coverage metrics for generative models. ICML 2020.

Preprocessing scripts: from dicom to aligned nitfy for SynthRAD2023 Grand Challenge

[MedIA Journal] An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models

[COMMSENG'24, TMI'24] Interactive Computer-Aided Diagnosis using LLMs

An open source implementation of CLIP.

Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。

[CVPR 2025 Highlight] Official implementation of "Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity"

Code for ICLR'24 workshop ME-FoMo-How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation

异常/缺陷检测方向，谷歌学术和arxiv论文的相关更新

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

[AAAI 2024] MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities

[ICLR2025] Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Pytorch Implementation of "SMITE: Segment Me In TimE" (ICLR 2025)