Unified Perceptual Parsing for Scene Understanding [chapter]

Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun
2018 Lecture Notes in Computer Science  
Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from
more » ... terogeneous image annotations. We benchmark our framework on Unified Perceptual Parsing and show that it is able to effectively segment a wide range of concepts from images. The trained networks are further applied to discover visual knowledge in natural scenes 1 .
doi:10.1007/978-3-030-01228-1_26 fatcat:bopejhyckrfwpe7575xt2vz2je