RBC: Rectifying the Biased Context in Continual Semantic Segmentation
Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In practice, new images are usually made available in a consecutive manner, leading to a problem called Continual Semantic Segmentation (CSS). Typically, CSS faces the forgetting problem since previous training images are unavailable, and the semantic shift problem of the background class. Considering the semantic segmentation as a context-dependent pixel-level classification task, we explore CSS from a new perspective of context analysis in this paper. We observe that the context of old-class pixels in the new images is much more biased on new classes than that in the old images, which can sharply aggravate the old-class forgetting and new-class overfitting. To tackle the obstacle, we propose a biased-context-rectified CSS framework with a context-rectified image-duplet learning scheme and a biased-context-insensitive consistency loss. Furthermore, we propose an adaptive re-weighting class-balanced learning strategy for the biased class distribution. Our approach outperforms state-of-the-art methods by a large margin in existing CSS scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual Semantic SegmentationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
Few-shot semantic segmentation (FSS) has achieved great success on segmenting objects of novel classes, supported by only a few annotated samples. However, existing FSS methods often underperform in the presence of domai…
Cross-Domain Few-ShotFew-Shot Semantic SegmentationSegmentationSemantic SegmentationSR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper,…
Generative Adversarial NetworkZero-Shot LearningContinual Attentive Fusion for Incremental Learning in Semantic Segmentation
Over the past years, semantic segmentation, as many other tasks in computer vision, benefited from the progress in deep neural networks, resulting in significantly improved performance. However, deep architectures traine…
Incremental LearningSemantic SegmentationCPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation
Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel …
Active LearningSemantic SegmentationRepresentation Compensation Networks for Continual Semantic Segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-pa…
Class Incremental LearningContinual LearningContinual Semantic SegmentationDisjoint 10-1+15