September
2014
Towards Transparent Systems: Semantic Characterization of Failure Modes
Authors:
Abstract:
Today’s computer vision systems are not perfect. They fail frequently. Even worse, they fail abruptly and seemingly inexplicably. We argue that making our systems more transparent via an explicit hu- man understandable characterization of their failure modes is desirable. We propose characterizing the failure modes of a vision system using semantic attributes. For example, a face recognition system may say “If the test image is blurry, or the face is not frontal, or the person to be recognized is a young white woman with heavy make up, I am likely to fail.” This information can be used at training time by researchers to design better features, models or collect more focused training data. It can also be used by a downstream machine or human user at test time to know when to ignore the output of the system, in turn making it more reliable. To generate such a “specification sheet”, we discrimina- tively cluster incorrectly classified images in the semantic attribute space using L1-regularized weighted logistic regression. We show that our spec- ification sheets can predict oncoming failures for face and animal species recognition better than several strong baselines. We also show that lay people can easily follow our specification sheets.
copied = false, 2000);
">
@conference{Bansal-2014-17149,
author = {Aayush Bansal And Ali Farhadi And Devi Parikh},
title = {Towards Transparent Systems: Semantic Characterization of Failure Modes},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2014},
month = {September},
pages = {366 - 381},
}
author = {Aayush Bansal And Ali Farhadi And Devi Parikh},
title = {Towards Transparent Systems: Semantic Characterization of Failure Modes},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2014},
month = {September},
pages = {366 - 381},
}