Continual learning approaches for anomaly detection
Open Access
- 18 September 2025
- journal article
- research article
- Published by Springer Nature in Evolving Systems
- Vol. 16 (4) , 1-20
Abstract
Anomaly detection (AD) is a relevant problem in numerous real-world applications, especially when dealing with images. However, in real-world applications, it is common that the input data distribution can change over time, decreasing performance significantly. Therefore, in this study, we investigate the problem of Visual Anomaly Detection at Pixel-Level in the Continual Learning setting, where the model adapts to the new data while maintaining the knowledge of old data. We implement and test several AD techniques and adapt them to work in the CL setting using the Replay approach. We evaluate them using the well-known MVTec AD Dataset, where each object corresponds to a new learning task. Moreover, a significant challenge when dealing with the Replay approach is the memory occupied to store a portion of past images, which could be too heavy for many resource-constrained systems. Therefore, we propose a novel approach called SCALE, which performs high compression levels while preserving image quality through Super-Resolution techniques. Using the SCALE method to compress replay memory, in conjunction with the AD technique Inpaint, allows for obtaining the best AD results while significantly reducing memory consumption.Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- An online continual object detector on VHR remote sensing images with class imbalanceEngineering Applications of Artificial Intelligence, 2022
- Online Continual Learning via the Meta-learning update with Multi-scale Knowledge Distillation and Data AugmentationEngineering Applications of Artificial Intelligence, 2022
- Imbalanced Continual Learning with Partitioning Reservoir Sampling2020
- Memory-Efficient Incremental Learning Through Feature Adaptation2020
- Lifelong generative modelingNeurocomputing, 2020
- Efficient continual learning in neural networks with embedding regularizationNeurocomputing, 2020
- GANomaly: Semi-supervised Anomaly Detection via Adversarial Training2019
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence2018
- Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights2018
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery2017