In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model generalises well to unseen images and requires a single forward pass to perform saliency detection, therefore suitable for use in real-time systems. We test our approach on CIFAR-10 and ImageNet datasets and show that the produced saliency maps are easily interpretable, sharp, and free of artifacts. We suggest a new metric for saliency and test our method on the ImageNet object localisation task. We achieve results outperforming other weakly supervised methods.

The paper proposes an approach to learn saliency masks. The proposed approach is based on a neural network and can process multiple images per second (i.e. it is fast). To me the paper is borderline, I would not object rejection or acceptance. I really believe in the concept of learning to explain a model and I think the paper has some good ideas. There are no obvious mistakes but there are clear limitations.

Pattern recognition systems implemented using deep neural networks achieve better results than linear models. However, their drawback is the black box property. This property means that one with no experience utilising nonlinear systems may need help understanding the outcome of the decision. Such a solution is unacceptable to the user responsible for the final decision. He must not only believe in the decision but also understand it. Therefore, recognisers must have an architecture that allows interpreters to interpret the findings. The idea of post-hoc explainable classifiers is to design an interpretable classifier parallel to the black box classifier, giving the same decisions as the black box classifier. This paper shows that the explainable classifier completes matching classification decisions with the black box classifier on the MNIST and FashionMNIST databases if Zadeh's fuzzy logic function forms the classifier and DeconvNet importance gives the truth values. Since the other tested significance measures achieved lower performance than DeconvNet, it is the optimal transformation of the feature values to their truth values as inputs to the fuzzy logic function for the databases and recogniser architecture used.

Artificial Intelligence (AI) has come to prominence as one of the major components of our society, with applications in most aspects of our lives. In this field, complex and highly nonlinear machine learning models such as ensemble models, deep neural networks, and Support Vector Machines have consistently shown remarkable accuracy in solving complex tasks. Although accurate, AI models often are "black boxes" which we are not able to understand. Relying on these models has a multifaceted impact and raises significant concerns about their transparency. Applications in sensitive and critical domains are a strong motivational factor in trying to understand the behavior of black boxes. We propose to address this issue by providing an interpretable layer on top of black box models by aggregating "local" explanations. We present GLocalX, a "local-first" model agnostic explanation method. Starting from local explanations expressed in form of local decision rules, GLocalX iteratively generalizes them into global explanations by hierarchically aggregating them. Our goal is to learn accurate yet simple interpretable models to emulate the given black box, and, if possible, replace it entirely. We validate GLocalX in a set of experiments in standard and constrained settings with limited or no access to either data or local explanations. Experiments show that GLocalX is able to accurately emulate several models with simple and small models, reaching state-of-the-art performance against natively global solutions. Our findings show how it is often possible to achieve a high level of both accuracy and comprehensibility of classification models, even in complex domains with high-dimensional data, without necessarily trading one property for the other. This is a key requirement for a trustworthy AI, necessary for adoption in high-stakes decision making applications.