Union-Set Multi-source Model Adaptation for Semantic Segmentation
Union-Set Multi-source Model Adaptation for Semantic Segmentation
复制标题
DOI：
10.1007/978-3-031-19818-2_33
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Zongyao Li;Ren Togo;Takahiro Ogawa;M. Haseyama
中科院分区：
文献类型：
--
作者：
Zongyao Li;Ren Togo;Takahiro Ogawa;M. Haseyama
本文解决了语义分割的多源模型自适应问题的广义版本。模型自适应被提出作为一个新的域自适应问题，它需要访问预先训练的模型而不是源域的数据。模型自适应的一般多源设置严格假设每个源域与目标域共享公共标签空间。作为一种放松，我们允许每个源域的标签空间是目标域标签空间的子集，并要求源域标签空间的并集等于目标域标签空间。对于联合集多源模型自适应的新设置，我们提出了一种采用模型不变特征学习的新颖学习策略的方法，该方法充分利用源域模型的多样性特征，从而提高目标域的泛化能力。我们在各种适应环境中进行了广泛的实验，以证明我们的方法的优越性。
This paper solves a generalized version of the problem of multi-source model adaptation for semantic segmentation. Model adaptation is proposed as a new domain adaptation problem which requires access to a pre-trained model instead of data for the source domain. A general multi-source setting of model adaptation assumes strictly that each source domain shares a common label space with the target domain. As a relaxation, we allow the label space of each source domain to be a subset of that of the target domain and require the union of the source-domain label spaces to be equal to the target-domain label space. For the new setting named union-set multi-source model adaptation, we propose a method with a novel learning strategy named model-invariant feature learning, which takes full advantage of the diverse characteristics of the source-domain models, thereby improving the generalization in the target domain. We conduct extensive experiments in various adaptation settings to show the superiority of our method.