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

Jyri Kivinen, Chris Williams, Nicolas Heess
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:512-521, 2014.

Abstract

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 \emphsquared 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v33-kivinen14, title = {{Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection}}, author = {Kivinen, Jyri and Williams, Chris and Heess, Nicolas}, booktitle = {Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics}, pages = {512--521}, year = {2014}, editor = {Kaski, Samuel and Corander, Jukka}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/kivinen14.pdf}, url = {https://proceedings.mlr.press/v33/kivinen14.html}, abstract = {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 \emphsquared 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.} }
Endnote
%0 Conference Paper %T Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection %A Jyri Kivinen %A Chris Williams %A Nicolas Heess %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-kivinen14 %I PMLR %P 512--521 %U https://proceedings.mlr.press/v33/kivinen14.html %V 33 %X 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 \emphsquared 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.
RIS
TY - CPAPER TI - Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection AU - Jyri Kivinen AU - Chris Williams AU - Nicolas Heess BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-kivinen14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 33 SP - 512 EP - 521 L1 - http://proceedings.mlr.press/v33/kivinen14.pdf UR - https://proceedings.mlr.press/v33/kivinen14.html AB - 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 \emphsquared 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. ER -
APA
Kivinen, J., Williams, C. & Heess, N.. (2014). Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 33:512-521 Available from https://proceedings.mlr.press/v33/kivinen14.html.

Related Material