Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation
Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this work, we argue that widely available web images can also be considered for the learning of new classes. To achieve this, firstly we introduce a strategy to select web images which are similar to previously seen examples in the latent space using a Fourier-based domain discriminator. Then, an effective caption-driven reharsal strategy is proposed to preserve previously learnt classes. To our knowledge, this is the first work to rely solely on web images for both the learning of new concepts and the preservation of the already learned ones in WILSS. Experimental results show that the proposed approach can reach state-of-the-art performances without using manually selected and annotated data in the incremental steps.
Code (1)
Tasks
Incremental LearningSemantic SegmentationSimilar Papers 제목 키워드 기반
Completely 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+3Class-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+4Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation
Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incr…
Incremental LearningSegmentationSemantic SegmentationIncremental 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 SegmentationModeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, …
SegmentationSemantic SegmentationWeakly supervised segmentationWeakly supervised Semantic Segmentation+1