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

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

A method to increase the speed and lower the memory footprint of existing vision transformers.

Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

Witness the aha moment of VLM with less than $3.

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

Fully open reproduction of DeepSeek-R1

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)

[CVPR 2023] Token Contrast for Weakly-Supervised Semantic Segmentation

Complementary Patch for Weakly Supervised Semantic Segmentation, ICCV21 (poster)

Platformio build of the ESP32 CameraWebServer code example

Esp32-cam拍摄照片发送给电脑，电脑跑StableDiffusion进行AI重绘

Jetson Nano with Ubuntu 20.04 image

🔥 官方推荐 🔥 RuoYi-Vue 全新 Pro 版本，优化重构所有功能。基于 Spring Boot + MyBatis Plus + Vue & Element 实现的后台管理系统 + 微信小程序，支持 RBAC 动态权限、数据权限、SaaS 多租户、Flowable 工作流、三方登录、支付、短信、商城、CRM、ERP、AI 大模型等功能。你的 ⭐️ Star ⭐️，是作者生发的动力！

关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

deep learning for image processing including classification and object-detection etc.

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

An open autonomous driving platform

An asynchronous/parallel method of AlphaGo Zero algorithm with Gomoku

VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem

DEL: Deep Embedding Learning for Efficient Image Segmentation

[TMI' 23] autoSMIM: Automatic Superpixel-based Masked Image Modeling for Skin Lesion Segmentation