Meta-SR: A Magnification-Arbitrary Network for Super-Resolution (CVPR2019)

TMI 2018. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

Implementation code of the paper: FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction, NeurIPS 2018

[CVPR2020] GhostNet: More Features from Cheap Operations

Keras Implementation of faster-rcnn

Generate a quantization parameter file for ncnn framework int8 inference

SiamRPN, SiamRPN++, unofficial implementation of "SiamRPN++" (CVPR2019), multi-GPUs, LMDB.

The First Place Solution of Kaggle iMaterialist (Fashion) 2019 at FGVC6

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection, CVPR2021

PyTorch implementation of EfficientNetV2 family

Cascade R-CNN in Detectron

The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"

Code for the 1st place model in Carvana Image Masking Challenge

Python Single Object Tracking Evaluation

Image Super-Resolution by Neural Texture Transfer

Code for 1st Place Solution in Intracranial Hemorrhage Detection Challenge @ RSNA2019

天池2019广东工业智造创新大赛 布匹疵点检测 天池水也太深了 季军解决方案

Keras implementation of MaskRCNN object detection.

Composite Backbone Network (AAAI20)

High-level batteries-included neural network training library for Pytorch

BiSeNet based on pytorch

detector for rotated-object based on CenterNet/基于CenterNet的旋转目标检测

A fork of Detectron2 with ResNeSt backbone

Code for CVPR 2019 paper "Libra R-CNN: Towards Balanced Learning for Object Detection"

Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).

This repo contains the code for our paper "A novel focal Tversky loss function and improved Attention U-Net for lesion segmentation" accepted at IEEE ISBI 2019.

[CVPR 2019, Oral] "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images" by Wuyang Chen*, Ziyu Jiang*, Zhangyang Wang, Kexin Cui, and Xiaoning Qian

Winning solution for the Kaggle TGS Salt Identification Challenge.

Diverse Branch Block: Building a Convolution as an Inception-like Unit

TGS Salt Identification