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 intrinsic properties of boundaries.
@article{arxiv.1302.5985,
title = {A Meta-Theory of Boundary Detection Benchmarks},
author = {Xiaodi Hou and Alan Yuille and Christof Koch},
journal= {arXiv preprint arXiv:1302.5985},
year = {2013}
}
Comments
NIPS 2012 Workshop on Human Computation for Science and Computational Sustainability