COCO
Abstract
The COCO (Common Objects in Context) dataset is a large-scale image dataset oriented to general computer vision tasks such as object detection, segmentation, and keypoint detection, which contains more than 330,000 images, 80 categories of common objects, and abundant contextual annotation information, and is widely used for the benchmarking of algorithm performance.
Fields of Study & Subjects
Advanced Neural Network Applications
Domain Adaptation and Few-Shot Learning
Visual Attention and Saliency Detection
Publication details
- Journal / source
- Figshare
- Publication date
- 1 January 2026
- Document type
- Dataset