https://paperswithcode.com/task/object-detection

https://paperswithcode.com/task/object-detection

About

 Edit

Object detection is the task of detecting instances of objects of a certain class within an image. 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 )

Benchmarks

TREND	DATASET	BEST METHOD	PAPER TITLE	PAPER	CODE	COMPARE
	COCO test-dev	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation			See all
	COCO minival	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation			See all
	PASCAL VOC 2007	Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale)	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation			See all
	CrowdHuman (full body)	Beta R-CNN	Beta R-CNN: Looking into Pedestrian Detection from Another Perspective			See all
	KITTI Cars Easy	Patches	Patch Refinement -- Localized 3D Object Detection			See all
	UAVDT	SpotNet	SpotNet: Self-Attention Multi-Task Network for Object Detection			See all
	KITTI Cars Moderate	Patches	Patch Refinement -- Localized 3D Object Detection			See all
	KITTI Cars Hard	Patches	Patch Refinement -- Localized 3D Object Detection			See all
	WiderPerson	IterDet (Faster RCNN, ResNet50, 2 iterations)	IterDet: Iterative Scheme for Object Detection in Crowded Environments			See all
	PASCAL VOC 2012	SSD512 (07+12+COCO)	SSD: Single Shot MultiBox Detector			See all
	Visual Genome	MSDN	Scene Graph Generation from Objects, Phrases and Region Captions			See all
	nuScenes	BIRANet(RGB+Radar)	Radar+RGB Attentive Fusion for Robust Object Detection in Autonomous Vehicles			See all
	UA-DETRAC	SpotNet	SpotNet: Self-Attention Multi-Task Network for Object Detection			See all
	PeopleArt	Fast R-CNN (VGG16)	Detecting People in Artwork with CNNs			See all
	India Driving Dataset	hybrid incremental net	On Generalizing Detection Models for Unconstrained Environments			See all
	BDD100k	hybrid incremental net	On Generalizing Detection Models for Unconstrained Environments			See all
	PASCAL Part 2010 - Animals	Attention-based Joint Detection of Object and Semantic Part	Attention-based Joint Detection of Object and Semantic Part			See all
	SUN-RGBD val	CDSSD	How To Extract Fashion Trends From Social Media? A Robust Object Detector With Support For Unsupervised Learning			See all
	DOTA	BBAVector + rh	Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors			See all
	KITTI Pedestrians Easy	Vote3Deep	Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks			See all
	KITTI Pedestrians Moderate	Vote3Deep	Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks			See all
	KITTI Pedestrians Hard	Vote3Deep	Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks			See all
	KITTI Cyclists Easy	Vote3Deep	Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks			See all
	KITTI Cyclists Moderate	Vote3Deep	Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks			See all
	KITTI Cyclists Hard	Vote3Deep	Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks			See all
	Extragalactic Planetary Nebulae	PNe within NGC1380 & NGC1404	Fornax 3D project: automated detection of planetary nebulae in the centres of early-type galaxies and first results			See all
	COCO+	RepPoints + Self-adaptation	Slender Object Detection: Diagnoses and Improvements			See all
	LVIS v1.0	Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation			See all

Greatest papers with code

Greatest  Latest   Without code

 

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

17 Apr 2017 • tensorflow/tensorflow • 

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

 Ranked #113 on Object Detection on COCO test-dev

IMAGE CLASSIFICATION OBJECT DETECTION

 154,064

 Paper
 Code

 

 

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

30 Apr 2020 • tensorflow/models • 

MobileDets also outperform MobileNetV2+SSDLite by 1. 9 mAP on mobile CPUs, 3. 7 mAP on EdgeTPUs and 3. 4 mAP on DSPs while running equally fast.

 

NEURAL ARCHITECTURE SEARCH OBJECT DETECTION

 69,125

 Paper
 Code