COCO-O

Name: COCO-O
Published: 2023-07-25
License: Unknown

Dataset Information

Modalities

Images

Languages

English

Introduced

2023

License

Unknown

Homepage

Official Website

Contents

Overview
Associated Benchmarks
Recent Benchmark Submissions
Research Papers

Overview

COCO-O(ut-of-distribution) contains 6 domains (sketch, cartoon, painting, weather, handmake, tattoo) of COCO objects which are hard to be detected by most existing detectors. The dataset has a total of 6,782 images and 26,624 labelled bounding boxes.

Variants: COCO-O

Associated Benchmarks

This dataset is used in 1 benchmark:

Object Detection - Metrics: Average mAP, Effective Robustness

Recent Benchmark Submissions

Task	Model	Paper	Date
Object Detection	DETA (Swin-L)	NMS Strikes Back	2022-12-12
Object Detection	GRiT (ViT-H)	GRiT: A Generative Region-to-text Transformer …	2022-12-01
Object Detection	EVA	EVA: Exploring the Limits of …	2022-11-14
Object Detection	InternImage-L (Cascade Mask R-CNN)	InternImage: Exploring Large-Scale Vision Foundation …	2022-11-10
Object Detection	YOLOv6-L6	YOLOv6: A Single-Stage Object Detection …	2022-09-07
Object Detection	YOLOv7-E6E	YOLOv7: Trainable bag-of-freebies sets new …	2022-07-06
Object Detection	FIBER-B (Swin-B)	Coarse-to-Fine Vision-Language Pre-training with Fusion …	2022-06-15
Object Detection	ViT-Adapter (BEiTv2-L)	Vision Transformer Adapter for Dense …	2022-05-17
Object Detection	ViTDet (ViT-H)	Exploring Plain Vision Transformer Backbones …	2022-03-30
Object Detection	ViTDet (ViT-H)	Exploring Plain Vision Transformer Backbones …	2022-03-30
Object Detection	DINO (Swin-L)	DINO: DETR with Improved DeNoising …	2022-03-07
Object Detection	ConvNeXt-XL (Cascade Mask R-CNN)	A ConvNet for the 2020s	2022-01-10
Object Detection	GLIP-L (Swin-L)	Grounded Language-Image Pre-training	2021-12-07
Object Detection	GLIP-T (Swin-T)	Grounded Language-Image Pre-training	2021-12-07
Object Detection	MViTV2-H (Cascade Mask R-CNN)	MViTv2: Improved Multiscale Vision Transformers …	2021-12-02
Object Detection	YOLOX-S	YOLOX: Exceeding YOLO Series in …	2021-07-18
Object Detection	YOLOX-X	YOLOX: Exceeding YOLO Series in …	2021-07-18
Object Detection	CBNetV2 (Swin-L)	CBNet: A Composite Backbone Network …	2021-07-01
Object Detection	PVTv2-B5 (Mask R-CNN)	PVT v2: Improved Baselines with …	2021-06-25
Object Detection	DyHead (ResNet-50)	Dynamic Head: Unifying Object Detection …	2021-06-15

Research Papers

Recent papers with results on this dataset:

NMS Strikes Back (2022) -
GRiT: A Generative Region-to-text Transformer for Object Understanding (2022) -
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale (2022) -
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions (2022) -
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications (2022) -
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (2022) -
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone (2022) -
Vision Transformer Adapter for Dense Predictions (2022) -
Exploring Plain Vision Transformer Backbones for Object Detection (2022) -
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection (2022) -
A ConvNet for the 2020s (2022) -
Grounded Language-Image Pre-training (2021) -
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection (2021) -
YOLOX: Exceeding YOLO Series in 2021 (2021) -
CBNet: A Composite Backbone Network Architecture for Object Detection (2021) -
PVT v2: Improved Baselines with Pyramid Vision Transformer (2021) -
Dynamic Head: Unifying Object Detection Heads with Attentions (2021) -
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection (2021) -
Instances as Queries (2021) -
USB: Universal-Scale Object Detection Benchmark (2021) -

External Links:

COCO-O

Overview edit

Associated Benchmarks

Recent Benchmark Submissions

Research Papers

Edit Dataset Information

Overview