COCO-Stuff

Common Objects in COntext-stuff

Dataset Information
Modalities
Images
Introduced
2018
License
Homepage

Overview

The Common Objects in COntext-stuff (COCO-stuff) dataset is a dataset for scene understanding tasks like semantic segmentation, object detection and image captioning. It is constructed by annotating the original COCO dataset, which originally annotated things while neglecting stuff annotations. There are 164k images in COCO-stuff dataset that span over 172 categories including 80 things, 91 stuff, and 1 unlabeled class.

Source: Image Colorization: A Survey and Dataset
Image Source: https://github.com/nightrome/cocostuff

Variants: COCO-Stuff-81, COCO-Stuff 256x256, COCO-Stuff-171, COCO-Stuff-27, COCO-Stuff full, COCO-Stuff-3, COCO-Stuff-15, COCO-Stuff test, COCO-Stuff Labels-to-Photos, COCO-Stuff 64x64, COCO-Stuff 128x128, COCO-Stuff

Associated Benchmarks

This dataset is used in 3 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Zero-Shot Semantic Segmentation OTSeg OTSeg: Multi-prompt Sinkhorn Attention for … 2024-03-21
Zero-Shot Semantic Segmentation OTSeg+ OTSeg: Multi-prompt Sinkhorn Attention for … 2024-03-21
Zero-Shot Semantic Segmentation MVP-SEG+ MVP-SEG: Multi-View Prompt Learning for … 2023-04-14
Zero-Shot Semantic Segmentation DeOP Open-Vocabulary Semantic Segmentation with Decoupled … 2023-04-03
Zero-Shot Semantic Segmentation ZegCLIP ZegCLIP: Towards Adapting CLIP for … 2022-12-07
Zero-Shot Semantic Segmentation FreeSeg FreeSeg: Free Mask from Interpretable … 2022-09-27
Sketch-to-Image Translation PITI Pretraining is All You Need … 2022-05-25
Zero-Shot Semantic Segmentation zsseg A Simple Baseline for Open-Vocabulary … 2021-12-29
Zero-Shot Semantic Segmentation ZegFormer Decoupling Zero-Shot Semantic Segmentation 2021-12-15
Zero-Shot Semantic Segmentation MaskCLIP+ Extract Free Dense Labels from … 2021-12-02
Zero-Shot Semantic Segmentation SIGN SIGN: Spatial-information Incorporated Generative Network … 2021-08-27
Zero-Shot Semantic Segmentation STRICT A Closer Look at Self-training … 2021-04-21
Zero-Shot Semantic Segmentation CaGNet Context-aware Feature Generation for Zero-shot … 2020-08-16
Zero-Shot Semantic Segmentation ZS5 Zero-Shot Semantic Segmentation 2019-06-03
Sketch-to-Image Translation SPADE Semantic Image Synthesis with Spatially-Adaptive … 2019-03-18
Sketch-to-Image Translation Pix2PixHD High-Resolution Image Synthesis and Semantic … 2017-11-30
Semantic Segmentation Deeplab v2 COCO-Stuff: Thing and Stuff Classes … 2016-12-12

Research Papers

Recent papers with results on this dataset: