Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models

Concept-based methods have emerged as a promising direction to develop interpretable neural networks in standard supervised settings. However, most works that study them in incremental settings assume either a static concept set across all experiences or assume that each experience relies on a distinct set of concepts. In this work, we study concept-based models in a more realistic, dynamic setting where new classes may rely on older concepts in addition to introducing new concepts themselves. We show that concepts and classes form a complex web of relationships, which is susceptible to degradation and needs to be preserved and augmented across experiences. We introduce new metrics to show that existing concept-based models cannot preserve these relationships even when trained using methods to prevent catastrophic forgetting, since they cannot handle forgetting at concept, class, and concept-class relationship levels simultaneously. To address these issues, we propose a novel method - MuCIL - that uses multimodal concepts to perform classification without increasing the number of trainable parameters across experiences. The multimodal concepts are aligned to concepts provided in natural language, making them interpretable by design. Through extensive experimentation, we show that our approach obtains state-of-the-art classification performance compared to other concept-based models, achieving over 2$\times$ the classification performance in some cases. We also study the ability of our model to perform interventions on concepts, and show that it can localize visual concepts in input images, providing post-hoc interpretations.

Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks

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.