Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems
This work addresses the need for better human-understandable explanations in XAI for image classification, though it appears incremental as it builds on existing auto-encoder and segmentation methods.
The paper tackles the problem of explaining image classification systems by proposing an XAI framework that uses auto-encoders to extract middle-level features for generating multiple explanations, with experimental tests on two image datasets showing encouraging results.
A central issue addressed by the rapidly growing research area of eXplainable Artificial Intelligence (XAI) is to provide methods to give explanations for the behaviours of Machine Learning (ML) non-interpretable models after the training. Recently, it is becoming more and more evident that new directions to create better explanations should take into account what a good explanation is to a human user. This paper suggests taking advantage of developing an XAI framework that allows producing multiple explanations for the response of image a classification system in terms of potentially different middle-level input features. To this end, we propose an XAI framework able to construct explanations in terms of input features extracted by auto-encoders. We start from the hypothesis that some autoencoders, relying on standard data representation approaches, could extract more salient and understandable input properties, which we call here \textit{Middle-Level input Features} (MLFs), for a user with respect to raw low-level features. Furthermore, extracting different types of MLFs through different type of autoencoders, different types of explanations for the same ML system behaviour can be returned. We experimentally tested our method on two different image datasets and using three different types of MLFs. The results are encouraging. Although our novel approach was tested in the context of image classification, it can potentially be used on other data types to the extent that auto-encoders to extract humanly understandable representations can be applied.