Deeply learning the messages in message passing inference
Date
2015
Authors
Lin, G.
Shen, C.
Reid, I.
Van Den Hengel, A.
Editors
Cortes, C.
Lawrence, N.
Lee, D.
Sugiyama, M.
Garnett, R.
Lawrence, N.
Lee, D.
Sugiyama, M.
Garnett, R.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Advances in neural information processing systems, 2015 / Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (ed./s), vol.2015-January, pp.361-369
Statement of Responsibility
Guosheng Lin, Chunhua Shen, Ian Reid, Anton van den Hengel
Conference Name
29th Annual Conference on Neural Information Processing Systems 2015 (NIPS 2015) (7 Dec 2015 - 12 Dec 2015 : Montreal)
Abstract
Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to directly estimate the messages in message passing inference for structured prediction with Conditional Random Fields CRFs). With such CNN message estimators, we obviate the need to learn or evaluate potential functions for message calculation. This confers significant efficiency for learning, since otherwise when performing structured learning for a CRF with CNN potentials it is necessary to undertake expensive inference for every stochastic gradient iteration. The network output dimension of message estimators is the same as the number of classes, rather than exponentially growing in the order of the potentials. Hence it is more scalable for cases that a large number of classes are involved. We apply our method to semantic image segmentation and achieve impressive performance, which demonstrates the effectiveness and usefulness of our CNN message learning method.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright © (2015) by Neural Information Processing Systems All rights reserved.