paper-with-me

Papers

Towards Human-Understandable Multi-Dimensional Concept Discovery

2025-03-24 · CVPR 2025 1 · Arne Grobrügge, Niklas Kühl, Gerhard Satzger, Philipp Spitzer

Concept-based eXplainable AI (C-XAI) aims to overcome the limitations of traditional saliency maps by converting pixels into human-understandable concepts that are consistent across an entire dataset. A crucial aspect of C-XAI is completeness, which measures how well a set of concepts explains a model's decisions. Among C-XAI methods, Multi-Dimensional Concept Discovery (MCD) effectively improves completeness by breaking down the CNN latent space into distinct and interpretable concept subspaces. However, MCD's explanations can be difficult for humans to understand, raising concerns about their practical utility. To address this, we propose Human-Understandable Multi-dimensional Concept Discovery (HU-MCD). HU-MCD uses the Segment Anything Model for concept identification and implements a CNN-specific input masking technique to reduce noise introduced by traditional masking methods. These changes to MCD, paired with the completeness relation, enable HU-MCD to enhance concept understandability while maintaining explanation faithfulness. Our experiments, including human subject studies, show that HU-MCD provides more precise and reliable explanations than existing C-XAI methods. The code is available at https://github.com/grobruegge/hu-mcd.

📄 PDF Abstract BibTeX arXiv:2503.18629

Code (1)

grobruegge/hu-mcd 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

A survey on Concept-based Approaches For Model Improvement

2024-03-21 · Avani Gupta, P J Narayanan

The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence…

DisentanglementExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Survey

Discovering Concept Directions from Diffusion-based Counterfactuals via Latent Clustering

2025-05-11 · Payal Varshney, Adriano Lucieri, Christoph Balada, Andreas Dengel 외

Concept-based explanations have emerged as an effective approach within Explainable Artificial Intelligence, enabling interpretable insights by aligning model decisions with human-understandable concepts. However, existi…

ClusteringcounterfactualExplainable artificial intelligence

CB-SLICE: Concept-Based Interpretable Error Slice Discovery

2026-05-28 · Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud, Mateja Jamnik arxiv

Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the root causes of their failures is critic…

A Field Guide to Scientific XAI: Transparent and Interpretable Deep Learning for Bioinformatics Research

2021-10-13 · Thomas P Quinn, Sunil Gupta, Svetha Venkatesh, Vuong Le

Deep learning has become popular because of its potential to achieve high accuracy in prediction tasks. However, accuracy is not always the only goal of statistical modelling, especially for models developed as part of s…

Deep LearningExplainable Artificial Intelligence (XAI)scientific discovery

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

2023-05-27 · Kaiwen Xu, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma

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 positi…

Deep Learningimage-classificationImage Classification