Please open an issue for questions, comments, and bug reports. The goal of this benchmark is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. It is similar to semantic segmentation tasks in COCO and Pascal Dataset, but the data is more scene-centric and with a diverse range of object categories. The data for this benchmark comes from ADE20K Dataset (the full dataset will be released after the benchmark) which contains more than 20K scene-centric images exhaustively annotated with objects and object parts. Specifically, the benchmark data is divided into 20K images for training, 2K images for validation, and another batch of held-out images for testing. There are in total 150 semantic categories included in the benchmark for evaluation, which include stuffs like sky, road, grass, and discrete objects like person, car, bed. Note that non-uniform distribution of objects occurs in the images, mimicking a more natural object occurrence in daily scenes.