Transparent Anomaly Detection via Concept-based Explanations

2023-10-16 · Laya Rafiee Sevyeri, Ivaxi Sheth, Farhood Farahnak, Samira Ebrahimi Kahou, Shirin Abbasinejad Enger

Advancements in deep learning techniques have given a boost to the performance of anomaly detection. However, real-world and safety-critical applications demand a level of transparency and reasoning beyond accuracy. The task of anomaly detection (AD) focuses on finding whether a given sample follows the learned distribution. Existing methods lack the ability to reason with clear explanations for their outcomes. Hence to overcome this challenge, we propose Transparent {A}nomaly Detection {C}oncept {E}xplanations (ACE). ACE is able to provide human interpretable explanations in the form of concepts along with anomaly prediction. To the best of our knowledge, this is the first paper that proposes interpretable by-design anomaly detection. In addition to promoting transparency in AD, it allows for effective human-model interaction. Our proposed model shows either higher or comparable results to black-box uninterpretable models. We validate the performance of ACE across three realistic datasets - bird classification on CUB-200-2011, challenging histopathology slide image classification on TIL-WSI-TCGA, and gender classification on CelebA. We further demonstrate that our concept learning paradigm can be seamlessly integrated with other classification-based AD methods.

📄 PDF Abstract BibTeX arXiv:2310.10702

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection ClassificationGender Classificationimage-classification Image Classification

Explainable Visual Anomaly Detection via Concept Bottleneck Models

2025-11-25 · Arianna Stropeni, Valentina Zaccaria, Francesco Borsatti, Davide Dalle Pezze 외 arxiv

In recent years, Visual Anomaly Detection (VAD) has gained significant attention due to its ability to identify defects using only normal images during training. Many VAD models work without supervision but are still abl…

Anomaly Detection

ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection

2026-04-20 · Qiuhui Chen, Jiaxiang Song, Shuai Tan, Weimin Zhong arxiv

Deep learning-based industrial anomaly detectors often behave as black boxes, making it hard to justify decisions with physically meaningful defect evidence. We propose ZSG-IAD, a multimodal vision-language framework for…

Anomaly Detection Point Clouds

Explainable Anomaly Detection: Counterfactual driven What-If Analysis

2024-08-21 · Logan Cummins, Alexander Sommers, Sudip Mittal, Shahram Rahimi 외

There exists three main areas of study inside of the field of predictive maintenance: anomaly detection, fault diagnosis, and remaining useful life prediction. Notably, anomaly detection alerts the stakeholder that an an…

Anomaly Detection counterfactual Explainable artificial intelligence Fault Diagnosis

SADDE: Semi-supervised Anomaly Detection with Dependable Explanations

2024-11-18 · Yachao Yuan, Yu Huang, Yali Yuan, Jin Wang

Semi-supervised learning holds a pivotal position in anomaly detection applications, yet identifying anomaly patterns with a limited number of labeled samples poses a significant challenge. Furthermore, the absence of in…

Anomaly Detection Semi-supervised Anomaly Detection Supervised Anomaly Detection

AnomalyExplainer Explainable AI for LLM-based anomaly detection using BERTViz and Captum

2025-08-26 · Prasasthy Balasubramanian, Dumindu Kankanamge, Ekaterina Gilman, Mourad Oussalah arxiv

Conversational AI and Large Language Models (LLMs) have become powerful tools across domains, including cybersecurity, where they help detect threats early and improve response times. However, challenges such as false po…