Classification by Re-generation: Towards Classification Based on Variational Inference

TL;DR

This paper proposes a novel classification method using variational autoencoders for each class, enhancing interpretability, scalability, and robustness against adversarial examples.

Contribution

It introduces a class-specific VAE-based classification approach that improves scalability and includes a rejection criterion for uncertain or adversarial inputs.

Findings

The method allows class-specific training without retraining the entire network.

It improves interpretability of learned features.

The rejection criterion effectively filters out doubtful and adversarial examples.

Abstract

As Deep Neural Networks (DNNs) are considered the state-of-the-art in many classification tasks, the question of their semantic generalizations has been raised. To address semantic interpretability of learned features, we introduce a novel idea of classification by re-generation based on variational autoencoder (VAE) in which a separate encoder-decoder pair of VAE is trained for each class. Moreover, the proposed architecture overcomes the scalability issue in current DNN networks as there is no need to re-train the whole network with the addition of new classes and it can be done for each class separately. We also introduce a criterion based on Kullback-Leibler divergence to reject doubtful examples. This rejection criterion should improve the trust in the obtained results and can be further exploited to reject adversarial examples.