Scalable cascade inference for semantic image segmentation

Conference item

Semantic image segmentation is a problem of simultaneous segmentation and recognition of an input image into regions and their associated categorical labels, such as person, car or cow. A popular way to achieve this goal is to assign a label to every pixel in the input image and impose simple structural constraints on the output label space. Efficient approximation algorithms for solving this labelling problem such as a-expansion have, at best, linear runtime complexity with respect to the number of labels, making them practical only when working in a specific domain that has few classes-of-interest. However when working in a more general setting where the number of classes could easily reach tens of thousands, sub-linear complexity is desired. In this paper we propose meeting this requirement by performing cascaded inference that wraps around the a-expansion algorithm. The cascade both divides the large label set into smaller more manageable ones by way of a hierarchy, and dynamically subdivides the image into smaller and smaller regions during inference. We test our method on the SUN09 dataset with 107 accurately hand labelled classes.

Authors: Sturgess, P; Ladický, L; Crook, N; Torr, PHS

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: British Machine Vision Association
• Host title: Proceedings of the British Machine Vision Conference 2012
• Pages: 62.1-62.10
• Publication date: 2012-09-03
• Acceptance date: 2012-07-06
• Event title: British Machine Vision Conference 2012 (BMVC 2012)
• Event location: Guildford, Surrey, UK
• Event website: https://bmva-archive.org.uk/bmvc/2012/index.html
• Event start date: 2012-09-03
• Event end date: 2012-09-07
• EISBN: 1901725464
• Language: English