Abstract | ||
---|---|---|
Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safely perform. To jointly address these issues, we propose a method of learning confidence estimates for neural networks that is simple to implement and produces intuitively interpretable outputs. We demonstrate that on the task of out-of-distribution detection, our technique surpasses recently proposed techniques which construct confidence based on the networku0027s output distribution, without requiring any additional labels or access to out-of-distribution examples. Additionally, we address the problem of calibrating out-of-distribution detectors, where we demonstrate that misclassified in-distribution examples can be used as a proxy for out-of-distribution examples. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Machine Learning | Artificial intelligence,Artificial neural network,Detector,Mathematics,Machine learning |
DocType | Volume | Citations |
Journal | abs/1802.04865 | 6 |
PageRank | References | Authors |
0.42 | 10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Terrance Devries | 1 | 133 | 6.04 |
Graham W. Taylor | 2 | 1523 | 127.22 |