SimCS: Simulation for Domain Incremental Online Continual Segmentation
This addresses a practical challenge in applications like autonomous driving, where segmentation models need to adapt to new cities over time without forgetting, though it is incremental as it builds on existing methods.
The paper tackles the problem of Online Domain-Incremental Continual Segmentation (ODICS), where models learn from sequential data batches across domains with limited computation and no task boundaries, and shows that SimCS, a parameter-free method using simulated data for regularization, consistently improves existing continual learning methods in this setting.
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.