Predicting Failures of Vision Systems
CVPR(2014)
摘要
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.
更多查看译文
关键词
parameter estimation,alert,learning (artificial intelligence),semantic segmentation,image memorability prediction,image segmentation,vanishing point,zero-shot learning,image classification,attribute prediction,cameras,computer vision,classifiers,computer vision system failure prediction,camera parameter estimation,learning artificial intelligence,reliability,semantics,measurement,accuracy
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络