• SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications https://github.com/PengyiZhang/SlimYOLOv3

Object Detection in 20 Years: A Survey https://arxiv.org/abs/1905.05055

Recent Advances in Deep Learning for Object Detection https://www.arxiv-vanity.com/papers/1908.03673/

基于深度学习的目标检测最新进展（2013-2019） https://mp.weixin.qq.com/s/T6qeaj2K-rfZA7yrkWrhhA

• pytorch version of SSD and it's enhanced methods such as RFBSSD,FSSD and RefineDet https://github.com/lzx1413/PytorchSSD

• Single Shot Tracker https://github.com/shijieS/SST

【5大目标检测挑战与解决方案】《5 Significant Object Detection Challenges and Solutions》 https://medium.com/m/global-identity?redirectUrl=https%3A%2F%2Ftowardsdatascience.com%2F5-significant-object-detection-challenges-and-solutions-924cb09de9dd

卫星图像快速目标检测 https://github.com/CosmiQ/simrdwn

A higher performance PyTorch implementation of Single-Shot Refinement Neural Network for Object Detection https://github.com/luuuyi/RefineDet.PyTorch

【开源目标检测工具包(PyTorch)】’mmdetection - Open MMLab Detection Toolbox' by Multimedia Laboratory, https://github.com/open-mmlab/mmdetection

Official Tensorflow implementation of drl-RPN: Deep Reinforcement Learning of Region Proposal Networks (CVPR 2018 paper) https://github.com/aleksispi/drl-rpn-tf

Enriched Feature Guided Refinement Network for Detection，ICCV2019. https://github.com/Ranchentx/EFGRNet

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19) https://arxiv.org/abs/1904.01355 https://github.com/Adelaide-AI-Group/FCOS

Monocular 3D Object Detection https://github.com/kujason/monopsr

Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object Detection https://github.com/ParallelDots/generic-sku-detection-benchmark

PyTorch implementation for MatrixNet object detection architecture. https://github.com/arashwan/matrixnet

This is a pytorch implementation of VoVNet backbone networks as described in the paper An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. https://github.com/stigma0617/VoVNet.pytorch

YOLOv3 object detection architecture with uncertainty estimation. https://github.com/flkraus/bayesian-yolov3

ThunderNet: Towards Real-time Generic Object Detection https://github.com/ouyanghuiyu/Thundernet_Pytorch

Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters https://github.com/axelBarroso/Key.Net

yolov3 with mobilenet v2 and ASFF https://github.com/ruinmessi/ASFF

Code for calculating the upper bound AP in object detection https://github.com/aliborji/DeetctionUpperbound

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images https://github.com/dingjiansw101/RoITransformer_DOTA

Fast Learning of Temporal Action Proposal via Dense Boundary Generator! https://github.com/TencentYoutuResearch/ActionDetection-DBG

This project is the code for implementing the GridMask augmentation for image classification and object detection. https://github.com/akuxcw/GridMask

The implementation of "Towards accurate one-stage object detection with AP-loss" and its journal version. https://github.com/cccorn/AP-loss

A loss function (Weighted Hausdorff Distance) for object localization in PyTorch https://github.com/HaipengXiong/weighted-hausdorff-loss

Mask-Guided Attention Network for Occluded Pedestrian Detection. (ICCV'19) https://github.com/Leotju/MGAN

This project provides the implementation for DetNAS: Backbone Search for Object Detection. https://github.com/megvii-model/DetNAS

Paper: CVPR2018, Learning Rich Features for Image Manipulation Detection https://github.com/LarryJiang134/Image_manipulation_detection

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving (ICCV, 2019) https://github.com/jwchoi384/Gaussian_YOLOv3

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

https://github.com/becauseofAI/lffd-pytorch

《Accelerating Object Detection by Erasing Background Activations》 https://www.arxiv-vanity.com/papers/2002.01609/

CenterNet: Objects as Points in Tensorflow https://github.com/Stick-To/CenterNet-tensorflow

Feature pyramid network (FPN) with online hard example mining (OHEM) https://github.com/gurkirt/FPN.pytorch1.0

Reasoning-RCNN: Unifying Adaptive Global Reasoning into Large-scale Object Detection (CVPR2019 Oral) https://github.com/chanyn/Reasoning-RCNN

Lists the papers related to imbalance problems in object detection https://github.com/kemaloksuz/ObjectDetectionImbalance

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection https://github.com/garrickbrazil/M3D-RPN

The PyTorch Implementation of F-ConvNet for 3D Object Detection https://github.com/zhixinwang/frustum-convnet

【AdelaiDet：开源多实例级检测应用工具箱】 https://github.com/aim-uofa/adet

【面向目标检测标注的无人机图像及其YOLO模型】 https://github.com/chuanenlin/drone-net

【Detecto：用5行代码构建计算机视觉/目标检测模型的Python包】 https://github.com/alankbi/detecto

《Evaluating Weakly Supervised Object Localization Methods Right》 https://github.com/clovaai/wsolevaluation

PyTorch实现的DenseBox多任务学习目标检测/关键点定位

https://github.com/CaptainEven/DenseBox

Learning Spatial Fusion for Single-Shot Object Detection

https://github.com/ruinmessi/ASFF

【Elixir/Phoenix实时目标检测】 https://www.poeticoding.com/real-time-object-detection-with-phoenix-and-python/

【Sightseer：(TensorFlow 1.15)计算机视觉/目标检测最新预训练模型集成库 https://github.com/rish-16/sight

【YOLOv3各框架复现项目汇总(TensorFlow/PyTorch/Keras/Caffe/MXNet)】 https://github.com/amusi/YOLO-Reproduce-Summary

【路面坑洼检测】

https://github.com/JordanMicahBennett/Smart-Ai-Pothole-Detector------Powered-by-Tensorflow-TensorRT-on-Google-Colab-and-or-Jetson-Nano

【tf.keras实现的YOLOv3/v2目标检测pipeline】 https://github.com/david8862/keras-YOLOv3-model-set

【PyTorch实现的YOLOv3】 https://github.com/westerndigitalcorporation/YOLOv3-in-PyTorch

【ZazuML：面向实例检测的开源AutoML项目】 https://github.com/dataloop-ai/ZazuML

“目标检测和图像分类算法” https://www.bilibili.com/video/av80558087/

'基于CenterNet训练的目标检测器和姿态估计模型' tensorrt

https://github.com/bleakie/CenterMulti

'YOLOv3 Darknet GPU Inference API for Linux' https://github.com/BMW-InnovationLab/BMW-YOLOv3-Inference-API-GPU

【Tensorflow目标检测图形化训练界面 https://github.com/BMW-InnovationLab/BMW-TensorFlow-Training-GUI

【YOLO3的通道剪枝/层剪枝压缩】 https://github.com/tanluren/yolov3-channel-and-layer-pruning

'Strongeryolo-pytorch - Pytorch implementation of Stronger-Yolo with channel-pruning.' https://github.com/wlguan/Stronger-yolo-pytorch

Side-Aware Boundary Localization for More Precise Object Detection https://github.com/open-mmlab/mmdetection

【自动安全帽佩戴检测】’Automatic Hardhat Wearing Detection - Helmet Detection on Construction Sites' https://github.com/wujixiu/helmet-detection

'YOLOv3-complete-pruning - 对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求' https://github.com/coldlarry/YOLOv3-complete-pruning

Learning Lightweight Lane Detection CNNs by Self Attention Distillation https://github.com/cardwing/Codes-for-Lane-Detection

Data Priming Network for Automatic Check-Out - ACMMM 2019 https://github.com/lufficc/DPNet

行人检测(Pedestrian Detection)论文整理 https://github.com/xingkongliang/Pedestrian-Detection

'RFSong行人检测网络 - 重新设计的轻量级RFB进行行人检测，AP达到0.7993，参数量仅有3.1MB，200 FPS' https://github.com/songwsx/RFSong-7993

trident net + refinedet 目标检测 https://github.com/wei-yuma/multitrident

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection. https://arxiv.org/abs/1904.07392 https://github.com/DetectionTeamUCAS/NAS_FPN_Tensorflow

AnchorFreeDetection - list the paper for recently anchor free detector' https://github.com/VCBE123/AnchorFreeDetection

Light-Weight RetinaNet for Object Detection https://github.com/PSCLab-ASU/LW-RetinaNet

视频目标检测文献大列表 https://github.com/ZHANGHeng19931123/awesome-video-object-detection

A Keras implementation of CenterNet with pre-trained model (unofficial) https://github.com/see--/keras-centernet

Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting https://github.com/liuwei16/ALFNet

An mmdetection based implementation of updated Grid R-CNN published on CVPR 2019. https://github.com/STVIR/Grid-R-CNN

Python/YOLOv3自定义对象检测器实战指南 http://emaraic.com/blog/yolov3-custom-object-detector

RetinaNet: how Focal Loss fixes Single-Shot Detection https://towardsdatascience.com/retinanet-how-focal-loss-fixes-single-shot-detection-cb320e3bb0de

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). https://github.com/HRNet/HRNet-MaskRCNN-Benchmark

NAS-FCOS: Fast Neural Architecture Search for Object Detection https://arxiv.org/abs/1906.04423 https://github.com/Lausannen/NAS-FCOS

Some improvements about FCOS (FCOS: Fully Convolutional One-Stage Object Detection). https://github.com/yqyao/FCOS_PLUS

Focal Loss for Dense Rotation Object Detection https://github.com/DetectionTeamUCAS/RetinaNet_Tensorflow_Rotation

PyTorch code for locating objects without bounding boxes - Loss function and trained models

https://github.com/javiribera/locating-objects-without-bboxes

显著目标检测(SOD)代码大列表

https://github.com/jiwei0921/SOD-CNNs-based-code-summary-

Human vs Machine Attention in Neural Networks: A Comparative Study

https://arxiv.org/abs/1906.08764

YOLOv3-model-pruning - 对 YOLOv3 做模型剪枝（network slimming），对于 oxford hand 数据集，模型剪枝后的参数量减少 80%，Infer 的速度达到原来 2 倍，mAP 基本不变

https://github.com/Lam1360/YOLOv3-model-pruning

Grid R-CNN Plus: Faster and Better https://github.com/STVIR/Grid-R-CNN

卫星图像快速目标检测 小目标

https://github.com/avanetten/simrdwn

基于PyTorch的开源人群计数框架

https://github.com/gjy3035/C-3-Framework

This repository is the pytorch implementation for the crowd counting model, LSC-CNN, proposed in the paper - Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection. https://github.com/val-iisc/lsc-cnn

PyTorch codes for our paper "PCL: Proposal Cluster Learning for Weakly Supervised Object Detection".

https://github.com/ppengtang/pcl.pytorch

【目标检测】CornerNet: Detecting Objects as Paired Keypoints https://github.com/wenguanwang/DHF1K 本文是密歇根大学发表于ECCV 2018的工作。当前的目标检测算法大多基于Anchor，引入Anchor容易导致正负样本不均衡和引入更多超参数。本文在不采用Anchor的前提下取得了不错效果，是一篇非常有意思的探索工作。具体来说，论文借鉴了人体关键点检测的思路来做目标检测，通过检测目标框的左上角和右下角两个关键点就能得到预测框。其次，整个检测网络训练是从头开始的，且不基于预训练的分类模型，这使得用户能够自由设计特征提取网络，不用受预训练模型的限制。

This is a tensorflow implementation of R2CNN++: Multi-Dimensional Attention Based Rotation Invariant Detector with Robust Anchor Strategy. https://arxiv.org/abs/1811.07126 https://github.com/DetectionTeamUCAS/R2CNN-Plus-Plus_Tensorflow

Official implementation of paper "Learning Attraction Field Map for Robust Line Segment Detection" (CVPR 2019)

https://github.com/cherubicXN/afm_cvpr2019

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features https://github.com/mihaidusmanu/d2-net

(Python/OpenCV)Mask RCNN自动车牌识别系统 https://github.com/ria-com/nomeroff-net

YOLOv3/Darknet实现SOTA的Logo检测 https://platform.ai/blog/page/7/new-state-of-the-art-in-logo-detection-using-yolov3-and-darknet/

Code of Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (CVPR2019) https://github.com/wuzhe71/CPD

DSFD implement with pytorch https://github.com/yxlijun/DSFD.pytorch

Code for bottom-up object detection by grouping extreme and center points https://github.com/xingyizhou/ExtremeNet

Implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/ https://github.com/MaybeShewill-CV/lanenet-lane-detection

Spatial CNN for traffic lane detection (AAAI2018) https://github.com/XingangPan/SCNN

FCOS: Fully Convolutional One-Stage Object Detection https://github.com/tianzhi0549/FCOS https://github.com/DetectionTeamUCAS/FCOS_GluonCV

CenterNet is a framework for object detection with deep convolutional neural networks. https://github.com/Duankaiwen/CenterNet

Codebase for AAAI2019 "M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network"

https://github.com/qijiezhao/M2Det

FashionAI Key Points Detection using CPN model in Pytorch https://github.com/gathierry/FashionAI-KeyPointsDetectionOfApparel

Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow https://github.com/Qidian213/deep_sort_yolov3

Fast Online Object Tracking and Segmentation: A Unifying Approach http://www.robots.ox.ac.uk/~qwang/SiamMask/

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro https://github.com/qiaoguan/Person-reid-GAN-pytorch

Codebase of the paper "Feature Intertwiner for Object Detection", ICLR 2019 https://github.com/hli2020/feature_intertwiner

High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection, CVPR, 2019 https://github.com/liuwei16/CSP

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). https://github.com/HRNet/HRNet-Object-Detection

R2CNN: Rotational Region CNN Based on FPN (Tensorflow)

https://github.com/yangxue0827/R2CNN_FPN_Tensorflow

Bounding Box Regression with Uncertainty for Accurate Object Detection (CVPR'19)

https://github.com/yihui-he/KL-Loss

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

https://github.com/OceanPang/Libra_R-CNN

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Detection and Localization | KITTI https://github.com/Zengyi-Qin/MonoGRNet

Pytorch implementation of Bi-box Regression for Pedestrian Detection and Occlusion Estimation (ECCV2018) https://github.com/rainofmine/Bi-box_Regression

车道检测 https://github.com/amusi/awesome-lane-detection

[ECCV 2018] Spatial-Temporal Memory Networks for Video Object Detection https://github.com/fanyix/STMN

PyTorch实现的Detectron目标检测 https://github.com/adityaarun1/Detectron.pytorch

PyTorch实现的Yolo3 https://github.com/zhanghanduo/yolo3_pytorch

深度学习目标检测文献列表(技术路线) https://github.com/hoya012/deep_learning_object_detection

【目标检测】Gradient Harmonized Single-stage Detector 本文是香港中文大学发表于AAAI 2019的工作，文章从梯度的角度解决样本中常见的正负样本不均衡的问题。从梯度的角度给计算loss的样本加权，相比与OHEM的硬截断，这种思路和focal loss一样属于软截断，文章设计的思路不仅可以用于分类loss改进，对回归loss也很容易进行嵌入。不需要考虑focal loss的超参设计问题，同时文章提出的方法效果Focal Loss更好。创新点相当于FL的下一步方案，给出了解决class-imbalance的另一中思路，开了一条路，估计下一步会有很多这种方面的paper出现。 https://github.com/libuyu/GHM_Detection https://www.paperweekly.site/papers/2654

Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection https://github.com/yihui-he/softer-NMS

Code for my master thesis: Vehicle Detection and Pose Estimation for Autonomous Driving https://github.com/libornovax/master_thesis_code

目标识别神经网络评价 https://github.com/Cartucho/mAP

Crack-pot: Autonomous Road Crack and Pothole Detection https://github.com/sukhad-app/Crack-Pot

Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590). https://github.com/vacancy/PreciseRoIPooling

Faster R-CNN and Mask R-CNN in PyTorch 1.0 - Fast, modular reference implementation of Semantic Segmentation and Object Detection algorithms in PyTorch. https://github.com/facebookresearch/maskrcnn-benchmark

The implementation of “Gradient Harmonized Single-stage Detector” published on AAAI 2019. https://github.com/libuyu/GHM_Detection

YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers https://github.com/reu2018DL/YOLO-LITE

目标识别最新综述 https://www.paperweekly.site/papers/2461

SimpleDet：简单、通用的目标检测/实例识别框架 https://github.com/TuSimple/simpledet

BoxCars Fine-Grained Recognition of Vehicles https://github.com/JakubSochor/BoxCars