Semantic Scene Understanding through ADE20K dataset

We build up a pixel-wise annotated image dataset for scene parsing. Scene parsing network are also proposed to detect and segment visual concepts from any input images.

Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision. Despite the community’s efforts in data collection, there are still few image datasets covering a wide range of scenes and object categories with dense and detailed annotations for scene parsing. Here we provide a pixel-wise annotated dataset called ADE20K for scene parsing. It provides precise concept annotations in hierarchical levels, which allows closer look for semantic scene understanding.