A Simple Framework to Quantify Different Types of Uncertainty in Deep Neural Networks for Image Classification
This work addresses the problem of quantifying uncertainty in deep neural networks, which is crucial for increasing the safety of AI systems in high-stakes applications like autonomous vehicles and medical imaging.
The paper proposes a framework to quantify three types of uncertainty in Deep Neural Networks for image classification. It combines an ensemble of CNNs for model uncertainty, a supervised reconstruction auto-encoder for distributional uncertainty, and activation outputs for data uncertainty. The method's efficiency is demonstrated on popular image datasets.
Quantifying uncertainty in a model's predictions is important as it enables the safety of an AI system to be increased by acting on the model's output in an informed manner. This is crucial for applications where the cost of an error is high, such as in autonomous vehicle control, medical image analysis, financial estimations or legal fields. Deep Neural Networks are powerful predictors that have recently achieved state-of-the-art performance on a wide spectrum of tasks. Quantifying predictive uncertainty in DNNs is a challenging and yet on-going problem. In this paper we propose a complete framework to capture and quantify three known types of uncertainty in DNNs for the task of image classification. This framework includes an ensemble of CNNs for model uncertainty, a supervised reconstruction auto-encoder to capture distributional uncertainty and using the output of activation functions in the last layer of the network, to capture data uncertainty. Finally we demonstrate the efficiency of our method on popular image datasets for classification.