plot PR curve by COCO API and mmdet API

The code for "Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (AAAI 2022)"

D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration. ECCV, 2022

Official PyTorch implementation of "AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network" in CVPR 2022.

Centralized Feature Pyramid for Object Detection

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

unofficial EffcientDet implemented by mmdetection

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

A PyTorch implementation of EfficientNet

Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch

Resources for our paper "Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond"

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

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

Official implementation of the paper 'High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network' in CVPR 2021

VarifocalNet: An IoU-aware Dense Object Detector

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Official implementation of PVT series

Ultralytics YOLO 🚀

Code for our CVPR 2019 paper: Selective Kernel Networks; See zhihu：https://zhuanlan.zhihu.com/p/59690223

ResNeSt: Split-Attention Networks

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

an edge-real-time anchor-free object detector with decent performance

[ICCV 2017] Torch code for Grad-CAM

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

PaddlePaddle version Res2Net achieves 85.13% top-1 acc. on ImageNet.

Res2Net achieves SOTA on mmdetection.

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation