Weakly-supervised continual learning for class-incremental segmentation. (arXiv:2201.01029v1 [cs.CV])

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 …

arxiv cv incremental learning segmentation