COCO (Microsoft Common Objects in Context)

Introduced by Lin et al. in Microsoft COCO: Common Objects in Context

The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.

Splits: The first version of MS COCO dataset was released in 2014. It contains 164K images split into training (83K), validation (41K) and test (41K) sets. In 2015 additional test set of 81K images was released, including all the previous test images and 40K new images.

Based on community feedback, in 2017 the training/validation split was changed from 83K/41K to 118K/5K. The new split uses the same images and annotations. The 2017 test set is a subset of 41K images of the 2015 test set. Additionally, the 2017 release contains a new unannotated dataset of 123K images.

Task	Dataset Variant	Best Model
Object Detection	COCO minival	DINO
Object Detection	COCO test-dev	FD-SwinV2-G
Instance Segmentation	COCO minival	MasK DINO
Instance Segmentation	COCO test-dev	FD-SwinV2-G
Pose Estimation	COCO test-dev	ViTPose
Real-Time Object Detection	COCO	YOLOv7-E6E
Panoptic Segmentation	COCO test-dev	Mask DINO
Text-to-Image Generation	COCO	Parti
Few-Shot Object Detection	MS-COCO (10-shot)	imTED+ViT-B
Multi-Label Classification	MS-COCO	ADDS
Cross-Modal Retrieval	COCO 2014	BEiT-3
Keypoint Detection	COCO	4xRSN-50
Panoptic Segmentation	COCO minival	MasK DINO
Keypoint Detection	COCO test-dev	HRNet*
Multi-Person Pose Estimation	COCO	OmniPose
Multi-Person Pose Estimation	COCO test-dev	SCIO
Visual Question Answering	COCO Visual Question Answering (VQA) real images 1.0 open ended	MCB 7 att.
Real-time Instance Segmentation	MSCOCO	SparseInst-608
Open Vocabulary Object Detection	MSCOCO	Object-Centric-OVD
Visual Question Answering	COCO Visual Question Answering (VQA) real images 1.0 multiple choice	MCB 7 att.
Zero-Shot Cross-Modal Retrieval	COCO 2014	TCL
Single-object discovery	COCO_20k	TokenCut + CAD
Keypoint Detection	COCO test-challenge	4×RSN-50
Weakly-supervised instance segmentation	COCO test-dev	DiscoBox
Text-to-Image Generation	COCO 256 x 256	XMC-GAN
Object Counting	COCO count-test	ens
Object Detection	MSCOCO	PP-PicoDet-L
Image Captioning	COCO	ExpansionNet v2
Weakly Supervised Object Detection	COCO	MSLPD
Multi-Person Pose Estimation	COCO minival	HRNet-W48plus
Visual Question Answering	COCO Visual Question Answering (VQA) real images 2.0 open ended	HDU-USYD-UNCC
Region Proposal	COCO test-dev	GA-RPN
Question Generation	COCO Visual Question Answering (VQA) real images 1.0 open ended	MDN
Visual Question Answering	COCO Visual Question Answering (VQA) abstract images 1.0 open ended	Graph VQA
Object Detection	COCO 2017	MixMIM-L
Weakly Supervised Object Detection	COCO test-dev	wetectron
Visual Question Answering	COCO Visual Question Answering (VQA) abstract 1.0 multiple choice	Graph VQA
One-Shot Object Detection	COCO	OWL-ViT
Text-Image Retrieval	COCO (image as query)	Oscar
Image-level Supervised Instance Segmentation	COCO test-dev	LIID
object-detection	COCO	darknet-coco-object_detection
Pose Estimation	DensePose-COCO	Parsing R-CNN + ResNext101
Pose Estimation	COCO	PPT-L/D6
Unsupervised Semantic Segmentation	COCO-Stuff-3	IIC
Robust Object Detection	COCO	Faster R-CNN with Stylized Training Data
Text-Image Retrieval	COCO	Oscar
Real-Time Object Detection	COCO minival	Mask R-CNN X-152-32x8d
Conditional Image Generation	COCO-Animals	U-Net GAN
Layout-to-Image Generation	COCO-Stuff 256x256	OC-GAN
Open World Object Detection	COCO 2017 (Outdoor, Accessories, Appliance, Truck)	ORE
Open World Object Detection	COCO 2017 (Sports, Food)	ORE
Open World Object Detection	COCO 2017 (Electronic, Indoor, Kitchen, Furniture)	ORE
Knowledge Distillation	COCO	LSHFM
Zero-shot Text Retrieval	COCO	FLAVA
Zero-shot Image Retrieval	COCO	FLAVA
Zero-Shot Object Detection	MSCOCO	Object-Centric-OVD
Homography Estimation	COCO 2014	PFNet
Active Object Detection	COCO	RetinaNet
Instance Segmentation	coco minval	R3-CNN
Interactive Segmentation	COCO	IOG
Semi Supervised Learning for Image Captioning	COCO	Perturb, Predict & Paraphrase
Few-Shot Object Detection	COCO 2017	DETReg
Object Detection	COCO	REGO-Deformable DETR-X101
Pose Estimation	COCO minival	MSPN
Class-agnostic Object Detection	COCO	MDef-DETR
Object Proposal Generation	COCO	MDef-DETR
Panoptic Segmentation	COCO panoptic	VAN-B6*
Semantic Segmentation	COCO Visual Question Answering (VQA) real images 1.0 multiple choice	Ours256
Paraphrase Generation	MSCOCO	HRQ-VAE
Zero-Shot Object Detection	MS-COCO	ZSD-Polarity Loss
Point-Supervised Instance Segmentation	COCO test-dev	BESTIE
Object Detection	COCO+	RepPoints + Self-adaptation
Activeness Detection	COCO test-dev	Lightweight OpenPose
Real-Time Object Detection	COCO test-dev	YOLOR-P6
Weakly Supervised Object Detection	MSCOCO	CASD
Multi-object discovery	COCO_20k	Large-scale rOSD
Generalized Zero-Shot Object Detection	MS-COCO	Ours
One-Shot Instance Segmentation	COCO	Siamese Mask R-CNN

COCO (Microsoft Common Objects in Context)

Benchmarks Edit Add a new result Link an existing benchmark

Papers

Dataset Loaders Edit Add Remove

Tasks Edit

Similar Datasets

ADE20K

LVIS

RefCOCO

Flickr30k

Usage

License Edit

Modalities Edit

Languages Edit

Benchmarks

Add a new result Link an existing benchmark

Dataset Loaders

Add Remove

Tasks

License

Modalities

Languages