Semantic Understanding of Scenes through the ADE20K Dataset
This work addresses the problem of limited annotated data for scene parsing in computer vision, providing a new dataset and method that enhance parsing accuracy, though it is incremental in nature.
The authors tackled the lack of diverse and densely annotated datasets for scene parsing by introducing the ADE20K dataset, and they proposed a Cascade Segmentation Module that, when integrated into existing networks, significantly improved parsing performance across various scenes and objects.
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. In this paper, we introduce and analyze the ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. A generic network design called Cascade Segmentation Module is then proposed to enable the segmentation networks to parse a scene into stuff, objects, and object parts in a cascade. We evaluate the proposed module integrated within two existing semantic segmentation networks, yielding significant improvements for scene parsing. We further show that the scene parsing networks trained on ADE20K can be applied to a wide variety of scenes and objects.