基于生成建模的风格化对于回归任务中的域适应是否必要？
Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?
- University of Waterloo（滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文质疑回归任务中基于生成建模的输入级风格化的必要性，发现其作用有限，并提出非参数特征对齐方法 ImSty，在避免高计算开销的同时持续提升 SOTA 回归性能。
AI中文摘要：
无监督域适应（UDA）旨在目标域标签缺失的情况下弥合源域与目标域之间的差距，其采用两类主要技术：输入级对齐（例如生成建模和风格化）与特征级对齐（即匹配特征图的分布，例如梯度反转层）。受生成建模在图像分类中取得成功的启发，近期有研究将基于风格化的方法用于姿态估计等回归任务。然而，通过生成建模和风格化使用输入级对齐会带来额外开销与计算复杂度，从而限制其在真实世界 DA 任务中的应用。为研究输入级对齐在 DA 中的作用，我们提出以下问题：基于生成建模的风格化对于回归中的视觉域适应是否必要？令人惊讶的是，我们发现与分类相比，输入对齐对回归任务的影响很小。基于这些洞见，我们开发了一种非参数特征级域对齐方法——Implicit Stylization（隐式风格化，ImSty）——该方法无需计算密集型风格化和生成建模，即可在 SOTA 回归任务上取得持续提升。在生成建模与风格化也正日益受到域泛化领域欢迎之际，我们的工作对其作用进行了批判性评估。
英文摘要：
Unsupervised domain adaptation (UDA) aims to bridge the gap between source and target domains in the absence of target domain labels using two main techniques: input-level alignment (such as generative modeling and stylization) and feature-level alignment (which matches the distribution of the feature maps, e.g. gradient reversal layers). Motivated from the success of generative modeling for image classification, stylization-based methods were recently proposed for regression tasks, such as pose estimation. However, use of input-level alignment via generative modeling and stylization incur additional overhead and computational complexity which limit their use in real-world DA tasks. To investigate the role of input-level alignment for DA, we ask the following question: Is generative modeling-based stylization necessary for visual domain adaptation in regression? Surprisingly, we find that input-alignment has little effect on regression tasks as compared to classification. Based on these insights, we develop a non-parametric feature-level domain alignment method -- Implicit Stylization (ImSty) -- which results in consistent improvements over SOTA regression task, without the need for computationally intensive stylization and generative modeling. Our work conducts a critical evaluation of the role of generative modeling and stylization, at a time when these are also gaining popularity for domain generalization.
