E-ADDA：由新型马氏距离损失增强的面向智能计算的无监督对抗域适应
E-ADDA: Unsupervised Adversarial Domain Adaptation Enhanced by a New Mahalanobis Distance Loss for Smart Computing
AI总结：
本文提出E-ADDA无监督对抗域适应算法，通过新型马氏距离损失和OOD检测子程序强化域混淆，并在声学与视觉任务上取得显著优于现有方法的结果。
摘要：
在智能计算中，特定任务训练样本的标签并不总是充足。然而，一个相关但不同的数据集中的样本标签却是可用的。因此，研究人员依靠无监督域适应来利用一个数据集（源域）中的标签，从而在另一个不同的、无标签的数据集（目标域）中实现更好的分类。现有的UDA非生成式对抗方案旨在通过对抗训练实现域混淆。理想情况是实现完美的域混淆，但这一点并不能保证。为了在对抗训练的基础上进一步强化域混淆，我们提出了一种新颖的UDA算法E-ADDA，该算法同时使用了一种新颖的马氏距离损失变体和一个分布外检测子程序。马氏距离损失最小化编码后的目标样本与源域分布之间在分布层面的距离，从而在对抗训练之外施加额外的域混淆。随后，OOD子程序进一步剔除那些域混淆未成功的样本。我们在声学和计算机视觉两种模态上对E-ADDA进行了广泛而全面的评估。在声学模态中，以f1分数衡量，E-ADDA相较于若干最先进的UDA算法性能提升最高达29.8%。在计算机视觉模态中，评估结果表明，我们在Office-31和Office-Home等流行的UDA基准上取得了新的最先进性能，相较表现第二好的算法最高超出17.9%。
英文摘要：
In smart computing, the labels of training samples for a specific task are not always abundant. However, the labels of samples in a relevant but different dataset are available. As a result, researchers have relied on unsupervised domain adaptation to leverage the labels in a dataset (the source domain) to perform better classification in a different, unlabeled dataset (target domain). Existing non-generative adversarial solutions for UDA aim at achieving domain confusion through adversarial training. The ideal scenario is that perfect domain confusion is achieved, but this is not guaranteed to be true. To further enforce domain confusion on top of the adversarial training, we propose a novel UDA algorithm, \textit{E-ADDA}, which uses both a novel variation of the Mahalanobis distance loss and an out-of-distribution detection subroutine. The Mahalanobis distance loss minimizes the distribution-wise distance between the encoded target samples and the distribution of the source domain, thus enforcing additional domain confusion on top of adversarial training. Then, the OOD subroutine further eliminates samples on which the domain confusion is unsuccessful. We have performed extensive and comprehensive evaluations of E-ADDA in the acoustic and computer vision modalities. In the acoustic modality, E-ADDA outperforms several state-of-the-art UDA algorithms by up to 29.8%, measured in the f1 score. In the computer vision modality, the evaluation results suggest that we achieve new state-of-the-art performance on popular UDA benchmarks such as Office-31 and Office-Home, outperforming the second best-performing algorithms by up to 17.9%.
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。
