Predicting Failures of Vision Systems - Robotics Institute Carnegie Mellon University

Predicting Failures of Vision Systems

Peng Zhang, Jiuling Wang, Ali Farhadi, Martial Hebert, and Devi Parikh
Conference Paper, Proceedings of (CVPR) Computer Vision and Pattern Recognition, pp. 3566 - 3573, June, 2014

Abstract

Computer vision systems today fail frequently. They also fail abruptly without warning or explanation. Alleviating the former has been the primary focus of the community. In this work, we hope to draw the community’s attention to the latter, which is arguably equally problematic for real applications. We promote two metrics to evaluate failure prediction. We show that a surprisingly straightforward and general approach, that we call ALERT, can predict the likely accuracy (or failure) of a variety of computer vision systems - semantic segmentation, vanishing point and camera parameter estimation, and image memorability prediction - on individual input images. We also explore attribute prediction, where classifiers are typically meant to generalize to new unseen categories. We show that ALERT can be useful in predicting failures of this transfer. Finally, we leverage ALERT to improve the performance of a downstream application of attribute prediction: zero-shot learning. We show that ALERT can outperform several strong baselines for zero-shot learning on four datasets.

BibTeX

@conference{Zhang-2014-7841,
author = {Peng Zhang and Jiuling Wang and Ali Farhadi and Martial Hebert and Devi Parikh},
title = {Predicting Failures of Vision Systems},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2014},
month = {June},
pages = {3566 - 3573},
}