# A Case Study on Concept Induction for Neuron-Level Interpretability in CNN

Source: [A Case Study on Concept Induction for Neuron-Level Interpretability in CNN](<https://www.sota2.com/research/paper/69a66bdf2d603e6de3e3ccfc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-04T05:00:05.078Z

Authors: Moumita Sen Sarma, Samatha Ereshi Akkamahadevi, Pascal Hitzler

Published: 2026-02-27T08:07:47.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.00197>)

[PDF](<https://arxiv.org/pdf/2603.00197.pdf>)