Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the well-known domain shift problem. Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. However, most works conduct domain adaptation leveraging only the extracted features and reducing their domain shift from the perspective of loss function designs. In this paper, we argue that it is not sufficient to handle domain shift only based on domain-level features, but it is also essential to align such information on the feature space. Unlike previous works, we focus on the network design and propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. These layers are designed to match the feature distributions between different domains and can be easily applied to various MSDA methods. To show the robustness of our approach, we conducted an extensive experimental evaluation considering two challenging scenarios: digit recognition and object classification. The experimental results indicated that our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.
翻译:深入学习(DL)是各种计算机愿景任务的主要方法,因为其在许多任务上取得了相关成果。然而,在部分或没有标签数据的真实世界情景中,DL方法也容易出现众所周知的域变换问题。多源未经监督的域适应(MSDA)旨在通过从一个源模型包中分配微弱的知识,学习一个未加标签域的预测器。然而,大多数工作仅利用提取的特性进行域适应,并从损失功能设计的角度减少其域变换。在本文中,我们认为仅根据域级特征处理域变换是不够的,但还必须在地貌空间上调整这类信息。与以往的工作不同,我们侧重于网络设计,并提议将多源化的DomaIn Confliance Tilles(MS-DIal)的多源版本纳入不同层次的预测器。这些层的设计符合不同域的特征分布,并且可以很容易地应用于各种MSDA方法。为了显示我们的方法的稳健性,我们进行了广泛的实验性评估,考虑两种具有挑战性的情景:数字识别和对象变M的收益。实验结果显示我们对M的等级的方法。实验结果可以改进。