DeepAI AI Chat
Log In Sign Up

Learning with Style: Continual Semantic Segmentation Across Tasks and Domains

by   Marco Toldo, et al.

Deep learning models dealing with image understanding in real-world settings must be able to adapt to a wide variety of tasks across different domains. Domain adaptation and class incremental learning deal with domain and task variability separately, whereas their unified solution is still an open problem. We tackle both facets of the problem together, taking into account the semantic shift within both input and label spaces. We start by formally introducing continual learning under task and domain shift. Then, we address the proposed setup by using style transfer techniques to extend knowledge across domains when learning incremental tasks and a robust distillation framework to effectively recollect task knowledge under incremental domain shift. The devised framework (LwS, Learning with Style) is able to generalize incrementally acquired task knowledge across all the domains encountered, proving to be robust against catastrophic forgetting. Extensive experimental evaluation on multiple autonomous driving datasets shows how the proposed method outperforms existing approaches, which prove to be ill-equipped to deal with continual semantic segmentation under both task and domain shift.


page 1

page 4

page 6

page 11

page 13

page 14

page 16


SimCS: Simulation for Online Domain-Incremental Continual Segmentation

Continual Learning is a step towards lifelong intelligence where models ...

Continual Learning for Class- and Domain-Incremental Semantic Segmentation

The field of continual deep learning is an emerging field and a lot of p...

Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation

Unsupervised Domain Adaptation (UDA) is a transfer learning task which a...

Weakly-supervised continual learning for class-incremental segmentation

Transfer learning is a powerful way to adapt existing deep learning mode...

Generative appearance replay for continual unsupervised domain adaptation

Deep learning models can achieve high accuracy when trained on large amo...

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

Deep neural networks are typically trained in a single shot for a specif...

Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network

State-of-the-art multimodal semantic segmentation approaches combining L...