Object Detection

3611 papers with code • 84 benchmarks • 251 datasets

Object Detection is a computer vision task in which the goal is to detect and locate objects of interest in an image or video. The task involves identifying the position and boundaries of objects in an image, and classifying the objects into different categories. It forms a crucial part of vision recognition, alongside image classification and retrieval.

The state-of-the-art methods can be categorized into two main types: one-stage methods and two stage-methods:

  • One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet.

  • Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.

The most popular benchmark is the MSCOCO dataset. Models are typically evaluated according to a Mean Average Precision metric.

( Image credit: Detectron )

Libraries

Use these libraries to find Object Detection models and implementations
64 papers
27,330
20 papers
2,910
See all 39 libraries.

Most implemented papers

Deep Residual Learning for Image Recognition

tensorflow/models CVPR 2016

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

YOLOv3: An Incremental Improvement

open-mmlab/mmdetection 8 Apr 2018

At 320x320 YOLOv3 runs in 22 ms at 28. 2 mAP, as accurate as SSD but three times faster.

YOLO9000: Better, Faster, Stronger

AlexeyAB/darknet CVPR 2017

On the 156 classes not in COCO, YOLO9000 gets 16. 0 mAP.

Focal Loss for Dense Object Detection

facebookresearch/detectron ICCV 2017

Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.

YOLOv4: Optimal Speed and Accuracy of Object Detection

AlexeyAB/darknet 23 Apr 2020

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy.

SSD: Single Shot MultiBox Detector

weiliu89/caffe 8 Dec 2015

Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

rbgirshick/py-faster-rcnn NeurIPS 2015

In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.

Mask R-CNN

tensorflow/models ICCV 2017

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

tensorflow/tensorflow 17 Apr 2017

We present a class of efficient models called MobileNets for mobile and embedded vision applications.

MobileNetV2: Inverted Residuals and Linear Bottlenecks

tensorflow/models CVPR 2018

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.