DSP：用于无监督领域自适应语义分割的双软粘贴算法
DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
摘要：
语义分割的无监督领域自适应（UDA）旨在使在标记源域上训练的分割模型适应于未标记的目标域。现有方法试图学习域不变特征，同时遭受大的域间隙，这使得难以正确对齐差异特征，特别是在初始训练阶段。为了解决这个问题，本文提出了一种新的双软粘贴（DSP）方法。具体地说，DSP采用长尾类优先采样策略从源域图像中选择类，并将相应的图像块以融合权值软粘贴到源和目标训练图像上。在技术上，我们采用平均教师框架进行领域自适应，其中粘贴的源和目标图像通过学生网络，而原始目标图像通过教师网络。输出级对齐是通过使用加权交叉熵损失对齐来自两个网络的目标融合图像的概率图来进行的。此外，通过使用加权最大平均差异损失来对齐来自学生网络的源图像和目标图像的特征图来进行特征级对齐。DSP有助于模型从中间域学习域不变特征，从而实现更快的收敛和更好的性能。在两个具有挑战性的基准上的实验证明了DSP的优越性。代码可在\url{https://github.com/GaoLii/DSP}上获得。
英文摘要：
Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering from large domain gaps that make it difficult to correctly align discrepant features, especially in the initial training phase. To address this issue, we propose a novel Dual Soft-Paste (DSP) method in this paper. Specifically, DSP selects some classes from a source domain image using a long-tail class first sampling strategy and softly pastes the corresponding image patch on both the source and target training images with a fusion weight. Technically, we adopt the mean teacher framework for domain adaptation, where the pasted source and target images go through the student network while the original target image goes through the teacher network. Output-level alignment is carried out by aligning the probability maps of the target fused image from both networks using a weighted cross-entropy loss. In addition, feature-level alignment is carried out by aligning the feature maps of the source and target images from student network using a weighted maximum mean discrepancy loss. DSP facilitates the model learning domain-invariant features from the intermediate domains, leading to faster convergence and better performance. Experiments on two challenging benchmarks demonstrate the superiority of DSP over state-of-the-art methods. Code is available at \url{https://github.com/GaoLii/DSP}.
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。
