paper-with-me

Papers

RBC: Rectifying the Biased Context in Continual Semantic Segmentation

2022-03-16 · Hanbin Zhao, Fengyu Yang, Xinghe Fu, Xi Li

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.

📄 PDF Abstract BibTeX arXiv:2203.08404

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Semantic SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation

2024-04-16 · CVPR 2024 1 · Jiapeng Su, Qi Fan, Guangming Lu, Fanglin Chen 외

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 Segmentation

SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning

2019-04-15 · Zihan Ye, Fan Lyu, Linyan Li, Qiming Fu 외

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 Learning

Continual Attentive Fusion for Incremental Learning in Semantic Segmentation

2022-02-01 · Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota 외

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 Segmentation

CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

2021-12-11 · Yu Qiao, Jincheng Zhu, Chengjiang Long, Zeyao Zhang 외

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 Segmentation

Representation Compensation Networks for Continual Semantic Segmentation

2022-03-10 · CVPR 2022 1 · Chang-Bin Zhang, Jia-Wen Xiao, Xialei Liu, Ying-Cong Chen 외

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