arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.00822cs.CV
收藏

语义感知的领域广义分割

Semantic-Aware Domain Generalized Segmentation

Sichuan University(四川大学);Monash University(莫纳什大学);Sun Yat-sen University(中山大学);University of Electronic Science and Technology of China(电子科技大学)

Duo Peng, Yinjie Lei, Munawar Hayat, Yulan Guo, Wen Li

摘要:

在源域上训练的深度模型在具有不同数据分布的看不见的目标域上进行评估时缺乏泛化能力。当我们无法访问用于适应的目标域样本时,问题变得更加明显。在本文中,我们解决域广义语义分割,其中分割模型被训练为域不变的,而不使用任何目标域数据。解决这个问题的现有方法将数据标准化为统一的分布。我们认为,虽然这样的标准化促进了全球规范化,所产生的功能是不够的歧视,以获得清晰的分割边界。为了增强类别之间的分离,同时促进域不变性,我们提出了一个框架,包括两个新的模块:语义感知规范化(SAN)和语义感知白化(SAW)。具体来说,SAN侧重于不同图像风格的特征之间的类别级中心对齐,而SAW则对已经中心对齐的特征实施分布式对齐。在SAN和SAW的帮助下,我们鼓励类内紧致性和类间可分性。我们通过对广泛使用的数据集(即GTAV,SYNTHIA,Cityscapes,Mapillary和BDDS)进行广泛的实验来验证我们的方法。我们的方法显示出显着的改进,现有的国家的最先进的各种骨干网络。代码可在https://github.com/leolyj/SAN-SAW上获得

英文摘要:

Deep models trained on source domain lack generalization when evaluated on unseen target domains with different data distributions. The problem becomes even more pronounced when we have no access to target domain samples for adaptation. In this paper, we address domain generalized semantic segmentation, where a segmentation model is trained to be domain-invariant without using any target domain data. Existing approaches to tackle this problem standardize data into a unified distribution. We argue that while such a standardization promotes global normalization, the resulting features are not discriminative enough to get clear segmentation boundaries. To enhance separation between categories while simultaneously promoting domain invariance, we propose a framework including two novel modules: Semantic-Aware Normalization (SAN) and Semantic-Aware Whitening (SAW). Specifically, SAN focuses on category-level center alignment between features from different image styles, while SAW enforces distributed alignment for the already center-aligned features. With the help of SAN and SAW, we encourage both intra-category compactness and inter-category separability. We validate our approach through extensive experiments on widely-used datasets (i.e. GTAV, SYNTHIA, Cityscapes, Mapillary and BDDS). Our approach shows significant improvements over existing state-of-the-art on various backbone networks. Code is available at https://github.com/leolyj/SAN-SAW

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。

↑