CaltechAUTHORS
  A Caltech Library Service

A Meta-Theory of Boundary Detection Benchmarks

Hou, Xiaodi and Yuille, Alan and Koch, Christof (2012) A Meta-Theory of Boundary Detection Benchmarks. In: NIPS 2012 Workshop on Human Computation for Science and Computational Sustainability, 3-6 December 2012, Lake Tahoe, Nevada. http://resolver.caltech.edu/CaltechAUTHORS:20130816-103412043

[img]
Preview
PDF - Submitted Version
See Usage Policy.

107Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20130816-103412043

Abstract

Human labeled datasets, along with their corresponding evaluation algorithms, play an important role in boundary detection. We here present a psychophysical experiment that addresses the reliability of such benchmarks. To find better remedies to evaluate the performance of any boundary detection algorithm, we propose a computational framework to remove inappropriate human labels and estimate the instrinsic properties of boundaries.


Item Type:Conference or Workshop Item (Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/1302.5985arXivUNSPECIFIED
Additional Information:The first author would like to thank Liwei Wang, Yin Li, Xi (Stephen) Chen, and Katrina Ligett. The research was supported by the ONR via an award made through Johns Hopkins University and by the Mathers Foundation.
Group:Koch Laboratory, KLAB
Funders:
Funding AgencyGrant Number
ONRUNSPECIFIED
Mathers FoundationUNSPECIFIED
Subject Keywords:Computer Vision and Pattern Recognition
Record Number:CaltechAUTHORS:20130816-103412043
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20130816-103412043
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:40704
Collection:CaltechAUTHORS
Deposited By: KLAB Import
Deposited On:04 Mar 2013 22:34
Last Modified:27 Aug 2013 23:26

Repository Staff Only: item control page