soeaver

caffe-model

Caffe models (including classification, detection and segmentation) and deploy files for famouse networks

Pytorch_Mask_RCNN

Converted from [tf+keras version MASK-RCNN](https://github.com/matterport/Mask_RCNN)

Parsing-R-CNN

Parsing R-CNN for Instance-Level Human Analysis

RP-R-CNN

Renovating Parsing R-CNN for Accurate Multiple Human Parsing

awesome-human-parsing

QANet

Quality-Aware Network

M2FP

Mask2Former for Parsing (M2FP)

AirNet-PyTorch

Implementation of the paper ''Attention Inspiring Receptive-fields Network''

pytorch-priv

Pytorch implementation for Classification, Semantic Segmentation and Object Detection

Hier-R-CNN

Hier R-CNN: Instance-level Human Parts Detection and A New Benchmark

CrossNet-PyTorch

pypriv

Python API for Deep Learning Development and Deployment

lvis-api

Python API for LVIS Dataset

Human-Parts

The Human-Parts dataset used in DID-Net.

QualityFormer

Quality Enhancement Network

AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

AI-generated-characters

AI-generated-character

CoOp

Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)

DeepVision

在我很多项目中用到的CV算法推理框架应用。

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

eql.detectron2

The official implementation of Equalization Loss for Long-Tailed Object Recognition (CVPR 2020) based on Detectron2. https://arxiv.org/abs/2003.05176

mmdetection

Open MMLab Detection Toolbox and Benchmark

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

mvits_for_class_agnostic_od

Multi-modal Transformers Excel at Class-agnostic Object Detection

NCL

[CVPR2022] This repository contains code for the paper "Nested Collaborative Learning for Long-Tailed Visual Recognition", published at CVPR 2022

Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

StyleGAN-nada

stylegan2-distillation

StyleNeRF

This is the open source implementation of the ICLR2022 paper "StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis"

TensoRF

Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields