CVPR 2026 论文和开源项目合集

A compressive benchmark for label noise in medical image.

[MICCAI 2025] Benchmarking Fundus Reading Skills of MLLMs

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

A powerful desktop app turning ppt to video with AI voiceover and subtitles

Skin changer for League of Legends (LOL)

Pytorch implementation of BiomedCLIP vision model with LoRA tuning

This is the implementation of our ICLR'24 paper "Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution".

This is a repository contains the implementation of our SIGIR'23 full paper From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval.

Official Code for our CVPR 2024 Paper "Diversified and Personalized Multi-rater Medical Image Segmentation" (Highlight)

[ECCV 2022] A generalized long-tailed challenge that incorporates both the conventional class-wise imbalance and the overlooked attribute-wise imbalance within each class. The proposed IFL together…

[ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift

A manual for new starters in our group

This repo is the official implementation of TMI2024 paper "Prompt-driven Latent Domain Generalization for Medical Image Classification".

[COLING'25] HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding

Fine-tune Segment-Anything Model with Lightning Fabric.

This repository contains demos I made with the Transformers library by HuggingFace.

Domain generalization benchmark for skin lesion recognition, MICCAI 2023

[ACLW'24] LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition

[CVPR2021] DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets

Collect some resource about Segment Anything (SAM), including the latest papers and demo

Entry to the 2023 Scroll Prize

A curated list of prompt-based paper in computer vision and vision-language learning.

End-to-end web app using Flask for image classification

code for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"

This is the code of Glaucoma Grading from Multi-Modality imAges. Task 1 is glaucoma grading, task 2 is macular fovea localization, and task 3 is optic disc/cup segmentation.

An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.