Predicting Failures of Vision Systems

Peng Zhang, Jiuling Wang, Ali Farhadi, Martial Hebert, Devi Parikh
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
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
more » ... y of computer vision systems -semantic segmentation, vanishing point and camera parameter estimation, and image memorability predictionon 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.
doi:10.1109/cvpr.2014.456 dblp:conf/cvpr/ZhangWFHP14 fatcat:pbbsg5igpzc5lfx3fqx6drgvoe