Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing

Abstract

Although neural networks (especially deep neural networks) have achieved better-than-human performance in many fields, their real-world deployment is still questionable due to the lack of awareness about the limitations in their knowledge. To incorporate such awareness in the machine learning model, prediction with reject option (also known as selective classification or classification with abstention) has been proposed in the literature. In this paper, we present a systematic review of the prediction with the reject option in the context of various neural networks. To the best of our knowledge, this is the first study focusing on this aspect of neural networks. Moreover, we discuss different novel loss functions related to the reject option and post-training processing (if any) of network output for generating suitable measurements for knowledge awareness of the model. Finally, we address the application of the rejection option in reducing the prediction time for real-time problems and present a comprehensive summary of the techniques related to the reject option in the context of a wide variety of neural networks. Our code is available on GitHub: https://github.com/MehediHasanTutul/Reject_option.