LabelBank: Revisiting Global Perspectives for Semantic Segmentation

LabelBank: Revisiting Global Perspectives for Semantic Segmentation

Guang-Tong Zhou, Hexiang Hu, Zhiwei Deng, Fei Sha, Greg Mori

01 April 2017

Semantic segmentation requires a detailed labeling of image pixels by object category. Information derived from local image patches is necessary to describe the detailed shape of individual objects. However, this information is ambiguous and can result in noisy labels. Global inference of image content can instead capture the general semantic concepts present. We advocate that holistic inference of image concepts provides valuable information for detailed pixel labeling. We propose a generic framework to leverage holistic information in the form of a LabelBank for pixel-level segmentation. We show the ability of our framework to improve semantic segmentation performance in a variety of settings. We learn models for extracting a holistic LabelBank from visual cues, attributes, and/or textual descriptions. We demonstrate improvements in semantic segmentation accuracy on standard datasets across a range of state-of-the-art segmentation architectures and holistic inference approaches.

Venue : IEEE International Conference on Computer Vision (ICCV), Venice, Italy, October 22-29, 2017.

File Name : LabelBank.pdf