Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection

Jyri Kivinen, Christopher K. I. Williams, Nicolas Heess

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This paper investigates visual boundary detection, i.e. prediction of the presence of a boundary at a given image location. We develop a novel neurally-inspired deep architecture for the task. Notable aspects of our work are (i) the use of “covariance features” [Ranzato and Hinton, 2010] which depend on the squared response of a filter to the input image, and (ii) the integration of image information from multiple scales and semantic levels via multiple streams of interlinked, layered, and non-linear “deep” processing. Our results on the Berkeley Segmentation Data Set 500 (BSDS500) show comparable or better performance to the top-performing methods [Arbelaez et al., 2011, Ren and Bo, 2012, Lim et al., 2013, Dollár and Zitnick, 2013] with effective inference times. We also propose novel quantitative assessment techniques for improved method understanding and comparison. We carefully dissect the performance of our architecture, feature-types used and training methods, providing clear signals for model understanding and development.
Original languageEnglish
Title of host publicationProceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics
Place of PublicationReykjavik, Iceland
PublisherJournal of Machine Learning Research: Workshop and Conference Proceedings
Pages512-521
Number of pages10
Volume33
Publication statusPublished - 2014
Event17th International Conference on Artificial Intelligence and Statistics - Reykjavik, Iceland
Duration: 22 Apr 201425 Apr 2014
https://www.aistats.org/aistats2014/

Conference

Conference17th International Conference on Artificial Intelligence and Statistics
Abbreviated titleAISTATS 2014
Country/TerritoryIceland
CityReykjavik
Period22/04/1425/04/14
Internet address

Fingerprint

Dive into the research topics of 'Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection'. Together they form a unique fingerprint.

Cite this