MetaFormer Baselines for Vision (TPAMI 2024)

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

DeepSurv is a deep learning approach to survival analysis.

(TMI-2024) Source-Free Active Domain Adaptation (SFADA) for GTV Segmentation across Multiple Hospitals

[ACM MM 2024] SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification

Generating highly accurate pathology reports from gigapixel whole slide images with HistoGPT

General Vision Benchmark, GV-B, a project from OpenGVLab

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

[CVPR 2024] Code for "Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation"

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Official implementation for "SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide Images"

Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。

LAVIS - A One-stop Library for Language-Vision Intelligence

[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

A library that integrates different Multi-Modal Fusion methods into a unified framework

Deep Learning-based Image Fusion: A Survey

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

[IEEE TMI 2024] Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification

The solution to cameyon16 and camelyon17 challenge and also to your own WSI data project.

数字人资料整理

Unofficial implementation of CVPR2022 paper DTFD-MIL. Use the official CAMELYON16 dataset instead of the .pickle file used in the official DTFT-MIL repo.

Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks - MICCAI 2021