Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks
This work addresses the need for inherently interpretable deep vision models to enable trustworthy AI for real-world perception tasks, representing an incremental advancement in ante-hoc explainable models.
The paper tackles the problem of enhancing interpretability and performance in visual classification by introducing a concept learning framework that uses generative adversarial networks to align learned concepts with human-interpretable properties, resulting in robust models with coherent concept activations.
This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and makes use of adversarial training. During training, the explanation module is optimized to extract visual concepts from the classifier's latent representations, while the GAN-based module aims to discriminate images generated from concepts, from true images. This joint training scheme enables the model to implicitly align its internally learned concepts with human-interpretable visual properties. Comprehensive experiments demonstrate the robustness of our approach, while producing coherent concept activations. We analyse the learned concepts, showing their semantic concordance with object parts and visual attributes. We also study how perturbations in the adversarial training protocol impact both classification and concept acquisition. In summary, this work presents a significant step towards building inherently interpretable deep vision models with task-aligned concept representations - a key enabler for developing trustworthy AI for real-world perception tasks.