让深度神经网络的标签对齐，提升无监督域适应的稳定性和效果。
A Strategy for Label Alignment in Deep Neural Networks
- 基于目标域数据矩阵的主奇异向量，设计标签对齐正则化。
- 在多个数据集上达到主流方法相当的性能，收敛更稳定。
- 适合需要稳定训练的无监督域适应场景，如跨域图像分类。
最近的研究在线性回归设置下成功应用了标签对齐特性于无监督域适应。该方法不正则化表示学习以实现域不变，而是正则化线性回归模型，使其与目标域数据矩阵的最高奇异向量对齐。本文将此思想拓展至深度学习场景，推导出适用于深度神经网络的标签对齐算法替代形式。实验表明，该方法在多个基准数据集上表现媲美主流无监督域适应方法，同时具有更稳定的收敛性。所有实验与代码已公开于：https://github.com/xuanrui-work/DeepLabelAlignment。
原文摘要 · Abstract (English)
One recent research demonstrated successful application of the label alignment property for unsupervised domain adaptation in a linear regression settings. Instead of regularizing representation learning to be domain invariant, the research proposed to regularize the linear regression model to align with the top singular vectors of the data matrix from the target domain. In this work we expand upon this idea and generalize it to the case of deep learning, where we derive an alternative formulation of the original adaptation algorithm exploiting label alignment suitable for deep neural network. We also perform experiments to demonstrate that our approach achieves comparable performance to mainstream unsupervised domain adaptation methods while having stabler convergence. All experiments and implementations in our work can be found at the following codebase: https://github.com/xuanrui-work/DeepLabelAlignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。