journalarticle
Attribution-Based Confidence Metric For Deep Neural Networks
Neural Information Processing Systems2019 66 citations69 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
No abstract is available from our sources. Use “Read paper” to view it.
TL;DRA novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs), which characterizes whether the output of a DNN on an input can be trusted and demonstrates the effectiveness of the ABC metric to make DNNs more trustworthy and resilient. (Semantic Scholar)