SimCS: simulation for domain incremental online continual segmentation

Conference item

Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual learning approaches mostly focus on image classification in the class-incremental setup with clear task boundaries and unlimited computational budget. This work explores the problem of Online Domain-Incremental Continual Segmentation (ODICS), where the model is continually trained over batches of densely labeled images from different domains, with limited computation and no information about the task boundaries. ODICS arises in many practical applications. In autonomous driving, this may correspond to the realistic scenario of training a segmentation model over time on a sequence of cities. We analyze several existing continual learning methods and show that they perform poorly in this setting despite working well in class-incremental segmentation. We propose SimCS, a parameter-free method complementary to existing ones that uses simulated data to regularize continual learning. Experiments show that SimCS provides consistent improvements when combined with different CL methods.

Authors: Alfarra, M; Cai, Z; Bibi, A; Ghanem, B; Müller, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Association for the Advancement of Artificial Intelligence
• Host title: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)
• Volume: 38
• Issue: 10
• Pages: 10795-10803
• Publication date: 2024-03-24
• Event title: 38th AAAI Conference on Artificial Intelligence (AAAI 2024)
• Event location: Vancouver, Canada
• Event website: https://aaai.org/aaai-conference/
• Event start date: 2024-02-20
• Event end date: 2024-02-27
• DOI: 10.1609/aaai.v38i10.28952
• EISSN: 2374-3468
• ISSN: 2159-5399
• Language: English
• Keywords: transfer; ML; multi-task learning; domain adaptation; life-long and continual learning