AdapTS: Lightweight Teacher-Student Approach for Multi-Class and Continual Visual Anomaly Detection
#AdapTS #teacher-student #visual anomaly detection #multi-class #continual learning #lightweight #computer vision
📌 Key Takeaways
- AdapTS introduces a lightweight teacher-student framework for visual anomaly detection.
- The approach supports multi-class anomaly detection across various object categories.
- It enables continual learning, adapting to new data without forgetting previous knowledge.
- The method is designed to be computationally efficient and scalable for real-world applications.
📖 Full Retelling
arXiv:2603.17530v1 Announce Type: cross
Abstract: Visual Anomaly Detection (VAD) is crucial for industrial inspection, yet most existing methods are limited to single-category scenarios, failing to address the multi-class and continual learning demands of real-world environments. While Teacher-Student (TS) architectures are efficient, they remain unexplored for the Continual Setting. To bridge this gap, we propose AdapTS, a unified TS framework designed for multi-class and continual settings, o
🏷️ Themes
Anomaly Detection, Machine Learning
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
arXiv:2603.17530v1 Announce Type: cross
Abstract: Visual Anomaly Detection (VAD) is crucial for industrial inspection, yet most existing methods are limited to single-category scenarios, failing to address the multi-class and continual learning demands of real-world environments. While Teacher-Student (TS) architectures are efficient, they remain unexplored for the Continual Setting. To bridge this gap, we propose AdapTS, a unified TS framework designed for multi-class and continual settings, o
Read full article at source