Weakly-supervised continual learning for class-incremental segmentation

01/04/2022
by   Gaston Lenczner, et al.
0

Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases in remote sensing. Starting from a neural network already trained for semantic segmentation, we propose to modify its label space to swiftly adapt it to new classes under weak supervision. To alleviate the background shift and the catastrophic forgetting problems inherent to this form of continual learning, we compare different regularization terms and leverage a pseudo-label strategy. We experimentally show the relevance of our approach on three public remote sensing datasets.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset