xue9981

OODSurvey

The Official Repository for "Generalized OOD Detection: A Survey"

pysot

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

MVTec-Anomaly-Detection

This project proposes an end-to-end framework for semi-supervised Anomaly Detection and Segmentation in images based on Deep Learning.

AnomalyDetection-M3DM

Code for CVPR 2023 paper "Multimodal Industrial Anomaly Detection via Hybrid Fusion"

AnomalyDetection-SoftPatch

Code for NeurIPS 2022 paper "SoftKernel: Unsupervised Anomaly Detection with Noisy Data"

EfficientFormer

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

TokenLabeling

Pytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

vision-retention-networks

Unofficial reimplementation of ViR: Vision Retention Networks by Hatamizadeh et. al. (https://arxiv.org/abs/2310.19731)

optuna

A hyperparameter optimization framework

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Paddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

self-attention-cv

Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.

awesome-industrial-anomaly-detection

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)。

Awesome-MIM

[Survey] Masked Modeling for Self-supervised Representation Learning on Vision and Beyond (https://arxiv.org/abs/2401.00897)

mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark

flash-attention

Fast and memory-efficient exact attention

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

MNN

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

Lighting-the-Darkness-in-the-Deep-Learning-Era-Open

wgpu

A cross-platform, safe, pure-Rust graphics API.

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

google-style-clang-format

A .clang-format file for Google C++ Style.

Awesome-Transformer-Attention

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

speedtest-cli

Command line interface for testing internet bandwidth using speedtest.net

sd_dreambooth_extension