Addressing Failure Prediction by Learning Model Confidence
This work addresses the critical need for reliable failure prediction in deep learning models, which is essential for their safe deployment in real-world applications, though it is incremental in improving confidence estimation.
The paper tackles the problem of predicting when deep neural networks will fail by introducing a new confidence criterion called True Class Probability (TCP), which consistently outperforms existing methods across various architectures and datasets.
Assessing reliably the confidence of a deep neural network and predicting its failures is of primary importance for the practical deployment of these models. In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP). We show how using the TCP is more suited than relying on the classic Maximum Class Probability (MCP). We provide in addition theoretical guarantees for TCP in the context of failure prediction. Since the true class is by essence unknown at test time, we propose to learn TCP criterion on the training set, introducing a specific learning scheme adapted to this context. Extensive experiments are conducted for validating the relevance of the proposed approach. We study various network architectures, small and large scale datasets for image classification and semantic segmentation. We show that our approach consistently outperforms several strong methods, from MCP to Bayesian uncertainty, as well as recent approaches specifically designed for failure prediction.