ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning

arXiv:2403.20126v1 Announce Type: new
Abstract: Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task. Despite recent progress with deep learning models, the dynamic nature of real-world applications necessitates continual learning, where models adapt to new classes (plasticity) over time without forgetting old ones (catastrophic forgetting). Current continual segmentation methods often rely on distillation strategies like knowledge distillation and pseudo-labeling, which are effective but result in increased training complexity and computational overhead. In this paper, we …

arxiv continual cs.cv eclipse panoptic segmentation prompt prompt tuning segmentation type visual