Unsupervised Domain Adaptation with Residual Transfer Networks
Mingsheng Long†, Han Zhu†, Jianmin Wang†, and Michael I. Jordan♯ †KLiss, MOE; TNList; School of Software, Tsinghua University, China ♯University of California, Berkeley, Berkeley, USA
Abstract
The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain. We relax a shared-classifier assumption made by previous methods and assume that the source classifier and target classifier differ by a residual function. We enable classifier adaptation by plugging several layers into deep network to explicitly learn the residual function with reference to the target classifier. We fuse features of multiple layers with tensor product and embed them into reproducing kernel Hilbert spaces to match distributions for feature adaptation. The adaptation can be achieved in most feed-forward models by extending them with new residual layers and loss functions, which can be trained efficiently via back-propagation. Empirical evidence shows that the new approach outperforms state of the art methods on standard domain adapta
中文速览
标注数据稀缺时，如何让深度模型从有标注的源域迁移到无标注的目标域，是领域自适应（domain adaptation）的核心难题。已有方法大多假设源域和目标域可以共用同一个分类器，只要特征对齐就够了，但这一假设在现实中往往过于乐观。本文提出残差迁移网络（Residual Transfer Network，RTN），放弃"共享分类器"假设，转而用残差层（residual layers）显式建模两个域分类器之间的偏差函数，让目标域分类器在回传梯度时自动向源域分类器靠拢并针对目标数据做出修正；同时用多层特征的张量积融合后嵌入再生核希尔伯特空间（RKHS）计算最大均值差异（MMD），实现特征分布的对齐，从而把分类器适配和特征适配统一在一个端到端框架里。在多个标准领域自适应基准上，RTN超过了当时所有对比方法，说明同时适配特征和分类器比单纯对齐特征更有效，对于源域与目标域分类边界差异较大的实际场景尤其有意义。
原文 arXiv:1602.04433;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1602.04433v2