Latent distillation for continual object detection at the edge

F Pasti, M Ceccon, DD Pezze, F Paissan… - arxiv preprint arxiv …, 2024 - arxiv.org
While numerous methods achieving remarkable performance exist in the Object Detection
literature, addressing data distribution shifts remains challenging. Continual Learning (CL) …

Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learning

N Bugarin, J Bugaric, M Barusco… - Proceedings of the …, 2024 - openaccess.thecvf.com
Anomaly Detection is a relevant problem in numerous real-world applications especially
when dealing with images. However little attention has been paid to the issue of changes …

Reverse Distillation for Continuous Anomaly Detection

A Yang, X Xu, Y Wu, H Liu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Unsupervised anomaly detection and localization methods only use anomaly-free images to
train the network. Ultimately, the network should be able to detect whether the input image …

Methodological Advancements in Continual Learning and Industry 4.0 Applications

D Dalle Pezze - 2023 - research.unipd.it
Abstract The Fourth Industrial Revolution, also known as Industry 4.0, is built on a variety of
technologies, including Artificial Intelligence, the Internet of Things, Cloud Computing …

Comparative Evaluation and Implementation of State-of-the-Art Techniques for Anomaly Detection and Localization in the Continual Learning Framework

N BUGARIN - thesis.unipd.it
The capability of anomaly detection (AD) to detect defects in industrial environments using
only normal samples has attracted significant attention. However, traditional AD methods …