arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.04813cs.CV
收藏

TACS:分类自适应跨领域语义分割

TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation

ETH Zurich(苏黎世联邦理工学院);MPI for Informatics(马克斯·普朗克信息学研究所);KU Leuven(鲁汶大学)

Rui Gong, Martin Danelljan, Dengxin Dai, Danda Pani Paudel, Ajad Chhatkuli, Fisher Yu, Luc Van Gool

摘要:

传统的领域自适应语义分割解决了在有限的或没有额外的监督下使模型适应新目标领域的任务。在处理输入域间隙时,标准领域自适应设置假定输出空间中没有域变化。在语义预测任务中,不同的数据集通常根据不同的语义分类进行标记。在许多实际环境中,目标域任务需要与源域所强加的分类不同的分类。因此,我们引入了更一般的分类自适应跨域语义分割(TACS)的问题,允许两个域之间的不一致的分类。我们进一步提出了一种方法,共同解决图像级和标签级的领域自适应。在标签级,我们采用双边混合抽样策略来扩大目标域,并重新标记的方法来统一和对齐标签空间。我们通过提出一种不确定性校正的对比学习方法来解决图像级的域差距,从而获得更多的域不变和类判别特征。我们广泛地评估我们的框架在不同的TACS设置的有效性:开放分类,粗到细分类,和隐式重叠分类。我们的方法优于以前的国家的最先进的大幅度,同时能够适应目标分类。我们的实现可以在www.example.com上公开获得。

英文摘要:

Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings assume no domain change in the output space. In semantic prediction tasks, different datasets are often labeled according to different semantic taxonomies. In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain. We therefore introduce the more general taxonomy adaptive cross-domain semantic segmentation (TACS) problem, allowing for inconsistent taxonomies between the two domains. We further propose an approach that jointly addresses the image-level and label-level domain adaptation. On the label-level, we employ a bilateral mixed sampling strategy to augment the target domain, and a relabelling method to unify and align the label spaces. We address the image-level domain gap by proposing an uncertainty-rectified contrastive learning method, leading to more domain-invariant and class-discriminative features. We extensively evaluate the effectiveness of our framework under different TACS settings: open taxonomy, coarse-to-fine taxonomy, and implicitly-overlapping taxonomy. Our approach outperforms the previous state-of-the-art by a large margin, while being capable of adapting to target taxonomies. Our implementation is publicly available at https://github.com/ETHRuiGong/TADA.

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。

↑