arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.04914cs.CV
收藏

部分领域自适应的深度残差校正网络

Deep Residual Correction Network for Partial Domain Adaptation

Beijing Institute of Technology(北京理工大学);Tsinghua University(清华大学);Indiana University-Purdue University Indianapolis(印第安纳大学-普渡大学印第安纳波利斯分校)

Shuang Li, Chi Harold Liu, Qiuxia Lin, Qi Wen, Limin Su, Gao Huang, Zhengming Ding

摘要:

深度领域自适应方法通过学习从良好标记的源域到不同但相关的未标记的目标域的可转移表示来实现吸引人的性能。现有的大多数工作假设源数据和目标数据共享相同的标签空间,这在许多实际应用中往往难以满足。随着大数据的出现,出现了一种更实际的场景,称为部分领域自适应,即我们总是可以访问更大规模的源域,同时处理相对较小规模的目标域。在这种情况下,传统的领域自适应假设应该放松,并且目标标签空间倾向于是源标签空间的子集。直觉上,增强最相关源子类的积极影响,减少不相关源子类的负面影响,对于解决部分领域自适应挑战至关重要。本文提出了一种高效实现的深度残差校正网络(DRCN),通过将一个残差块与特定任务的特征层一起插入源网络,有效地增强了从源到目标的适应性,并显式地削弱了不相关源类的影响。具体地说,由多个全连通层组成的插入残差块可以加深基本网络,相应地提高其特征表示能力。此外,我们设计了一个加权类域对齐损失耦合两个域之间的共享类源和目标的特征分布匹配。在部分、传统和细粒度跨域视觉识别上的综合实验表明,DRCN优于竞争激烈的深领域自适应方法。

英文摘要:

Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain. Most existing works assume source and target data share the identical label space, which is often difficult to be satisfied in many real-world applications. With the emergence of big data, there is a more practical scenario called partial domain adaptation, where we are always accessible to a more large-scale source domain while working on a relative small-scale target domain. In this case, the conventional domain adaptation assumption should be relaxed, and the target label space tends to be a subset of the source label space. Intuitively, reinforcing the positive effects of the most relevant source subclasses and reducing the negative impacts of irrelevant source subclasses are of vital importance to address partial domain adaptation challenge. This paper proposes an efficiently-implemented Deep Residual Correction Network (DRCN) by plugging one residual block into the source network along with the task-specific feature layer, which effectively enhances the adaptation from source to target and explicitly weakens the influence from the irrelevant source classes. Specifically, the plugged residual block, which consists of several fully-connected layers, could deepen basic network and boost its feature representation capability correspondingly. Moreover, we design a weighted class-wise domain alignment loss to couple two domains by matching the feature distributions of shared classes between source and target. Comprehensive experiments on partial, traditional and fine-grained cross-domain visual recognition demonstrate that DRCN is superior to the competitive deep domain adaptation approaches.

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。

↑