[2603.00197] A Case Study on Concept Induction for Neuron-Level Interpretability in CNN

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.00197 (cs) [Submitted on 27 Feb 2026] Title:A Case Study on Concept Induction for Neuron-Level Interpretability in CNN Authors:Moumita Sen Sarma, Samatha Ereshi Akkamahadevi, Pascal Hitzler View a PDF of the paper titled A Case Study on Concept Induction for Neuron-Level Interpretability in CNN, by Moumita Sen Sarma and 2 other authors View PDF HTML (experimental) Abstract:Deep Neural Networks (DNNs) have advanced applications in domains such as healthcare, autonomous systems, and scene understanding, yet the internal semantics of their hidden neurons remain poorly understood. Prior work introduced a Concept Induction-based framework for hidden neuron analysis and demonstrated its effectiveness on the ADE20K dataset. In this case study, we investigate whether the approach generalizes by applying it to the SUN2012 dataset, a large-scale scene recognition benchmark. Using the same workflow, we assign interpretable semantic labels to neurons and validate them through web-sourced images and statistical testing. Our findings confirm that the method transfers to SUN2012, showing its broader applicability. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.00197 [cs.CV]   (or arXiv:2603.00197v1 [cs.CV] for this version)   https://doi.org/10.48550/arXiv.2603.00197 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission histor...