# Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs

Source: [Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs](<https://www.sota2.com/research/paper/68fa71ed1e209131cea53977>)

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

Data updated: 2025-10-26T02:14:27.865Z

Authors: Kaiwen Xu, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma

Published: 2023-05-27T05:40:05.000Z

## Abstract

A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems. However, sometimes concept-based explanations may cause false positives, which misregards unrelated concepts as important for the prediction task. Our goal is to find the statistically significant concept for classification to prevent misinterpretation. In this study, we propose a method using a deep learning model to learn the image concept and then using the Knockoff samples to select the important concepts for prediction by controlling the False Discovery Rate (FDR) under a certain value. We evaluate the proposed method in our synthetic and real data experiments. Also, it shows that our method can control the FDR properly while selecting highly interpretable concepts to improve the trustworthiness of the model.

## 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/2305.18362>)

[PDF](<https://arxiv.org/pdf/2305.18362.pdf>)