A Survey on Assessing the Generalization Envelope of Deep Neural Networks at Inference Time for Image Classification

Deep Neural Networks (DNNs) achieve state-of-the-art performance on numerous problem set-ups. However, humans are not able to tell beforehand if a DNN receiving an input will deliver the desired output since their decision criteria are usually non-transparent. A DNN delivers the desired output if the input is within its generalization envelope. In this case, the information contained in the input sample is processed reasonably by the network. Since common DNNs fail to provide relevant information to assess the generalization envelope at inference time, additional methods or adaptations to the DNN have to be performed. Existing methods are evaluated using different set-ups respectively connected to three literature fields: predictive uncertainty, out-of-distribution detection and adversarial example detection. This survey connects those fields and gives an overview of the adaptations and methods that provide at inference time information if the current input is within the generalization area of a DNN.