Weakly-supervised continual learning for class-incremental segmentation
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. Code is open-source and released in this repository: https://github.com/alteia-ai/ICSS}{https://github.com/alteia-ai/ICSS.
Code (1)
Tasks
Continual LearningPseudo LabelSemantic SegmentationTransfer LearningSimilar Papers 제목 키워드 기반
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision
Instance segmentation requires labor-intensive manual labeling of the contours of complex objects in images for training. The labels can also be provided incrementally in practice to balance the human labor in differ…
Continual LearningIncremental LearningInstance SegmentationSegmentation+4RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensive pixel-level annotations to the traini…
Continual LearningImage SegmentationRelationSemantic SegmentationCompletely Weakly Supervised Class-Incremental Learning for Semantic Segmentation
This work addresses the task of completely weakly supervised class-incremental learning for semantic segmentation to learn segmentation for both base and additional novel classes using only image-level labels. While clas…
class-incremental learningClass Incremental LearningClass-Incremental Semantic SegmentationData Augmentation+3Continual Learning for Class- and Domain-Incremental Semantic Segmentation
The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in th…
class-incremental learningClass Incremental LearningClass-Incremental Semantic SegmentationContinual Learning+9Incremental Learning in Semantic Segmentation from Image Labels
Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensi…
Incremental LearningSegmentationSemantic Segmentation