Explainable Visual Anomaly Detection via Concept Bottleneck Models
cs.CV, cs.AI
Submitted: 2025-11-25
Updated: 2026-10-12
Terminology
Sources
- BMAD: Benchmarks for Medical Anomaly Detection
- SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
- PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
- LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
- Label-Free Concept Bottleneck Models
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
- Transparent Anomaly Detection via Concept-based Explanations
- Gemma 3 Technical Report
- Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models