2024/01/09 by Tanmay Garg, Garg, Tanmay, Deepika Vemuri +3
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Adversarial system #Artificial Intelligence (cs.AI) #Artificial intelligence #Cell Image Analysis Techniques #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Generative grammar #Interpretability #Machine Learning (cs.LG) #Machine learning #Robustness (evolution)
paper · pdf · doi:10.48550/arxiv.2401.04647
openalex publication_date 2024/01/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.