arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.06378cs.CV
收藏

语义图像分割:二十年的研究

Semantic Image Segmentation: Two Decades of Research

Naver Labs Europe

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii

摘要:

语义图像分割(SiS)在各种计算机视觉应用中起着基础作用,为图像的全局理解提供关键信息。这项调查旨在总结SiS领域二十年的研究,我们提出了从早期历史方法开始的解决方案文献综述,然后概述了最近的深度学习方法,包括最新趋势使用Transformers。我们通过讨论弱监督和侧机器学习技术的特定情况来补充审查,这些技术可用于改善语义分割,例如课程,增量或自监督学习。最先进的SiS模型依赖于大量带注释的样本,这些样本的获取比用于图像分类等任务的标签更昂贵。由于未标记数据的获取成本要低得多,因此无监督领域自适应(UDA)在语义分割社区中取得广泛成功也就不足为奇了。因此,本书的第二个核心贡献是总结了五年来快速发展的领域,语义图像分割的领域自适应(DASiS),它包含了语义分割本身的重要性和使分割模型适应新环境的迫切需要。除了提供一个全面的调查DASiS技术,我们还推出了新的趋势,如多域学习,领域泛化,域增量学习,测试时自适应和无源领域自适应。最后,我们通过描述SiS和DASiS中最广泛使用的数据集和基准来总结这项调查,并简要讨论相关任务,如实例和全景图像分割,以及医学图像分割等应用。

英文摘要:

Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning. State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this book is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends such as multi-domain learning, domain generalization, domain incremental learning, test-time adaptation and source-free domain adaptation. Finally, we conclude this survey by describing datasets and benchmarks most widely used in SiS and DASiS and briefly discuss related tasks such as instance and panoptic image segmentation, as well as applications such as medical image segmentation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑