all AI news
RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation
Feb. 20, 2024, 5:48 a.m. | Chang Liu, Giulia Rizzoli, Francesco Barbato, Andrea Maracani, Marco Toldo, Umberto Michieli, Yi Niu, Pietro Zanuttigh
cs.CV updates on arXiv.org arxiv.org
Abstract: Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed. In this paper, we extend our previous approach (RECALL) and tackle forgetting by exploiting unsupervised web-crawled data to retrieve examples of old classes from online databases. In contrast to the original methodology, which did not incorporate an assessment of web-based data, the present work proposes two …
abstract adversarial arxiv catastrophic forgetting continual cs.cv incremental issue knowledge paper recall regularization segmentation semantic strategies struggle through type unsupervised web
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
AI Engineering Manager
@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain