Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

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

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

Visual tracking library based on PyTorch.

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Awesome machine learning for combinatorial optimization papers.

单阶段通用目标检测器

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.

(2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on…

An unofficial Python wrapper for OpenAI's ChatGPT API

Two-stage CenterNet

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"

Two simple and effective designs of vision transformer, which is on par with the Swin transformer

python 3 pytorch implementation of DANN

[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention

[TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)

Global Tracking Transformers, CVPR 2022

SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (CVPR 2020, Oral)

MAST: A Memory-Augmented Self-supervised Tracker (CVPR 2020)

[ECCV 2020] Actions as Moving Points

D3S - Discriminative Single Shot Segmentation Tracker (CVPR 2020)

[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".

PointTrack (ECCV2020 ORAL): Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

CVPR2020 Oral && Best Paper Nomination

The official source code for the paper Consensus-Aware Visual-Semantic Embedding for Image-Text Matching (ECCV 2020)