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 2004.12615cs.CVcs.LGcs.MMstat.ML
收藏

领域自适应的最大密度发散

Maximum Density Divergence for Domain Adaptation

University of Electronic Science and Technology of China(电子科技大学);Shandong Normal University(山东师范大学);Indiana University-Purdue University Indianapolis(印第安纳大学与普渡大学印第安纳波利斯联合分校)

Li Jingjing, Chen Erpeng, Ding Zhengming, Zhu Lei, Lu Ke, Shen Heng Tao

摘要:

无监督领域自适应解决了将知识从一个良好标记的源域转移到一个未标记的目标域的问题,其中两个域具有不同的数据分布。因此,领域自适应的本质是减轻两个领域之间的分布分歧。最先进的方法通过进行对抗训练或最小化定义分布差距的度量来实践这一想法。在本文中,我们提出了一种新的领域自适应方法命名为对抗紧匹配(ATM),享有双方的优势对抗训练和度量学习。具体来说,首先,我们提出了一种新的距离损失,命名为最大密度发散(MDD),量化的分布分歧。MDD最小化了域间的分歧(ATM中的“匹配”),最大化了类内的密度(ATM中的“紧密”)。然后,为了解决对抗性领域自适应中的平衡挑战问题,我们考虑将所提出的MDD引入对抗性领域自适应框架。最后,我们将提出的MDD作为一个实际的学习损失,并报告我们的ATM。实证评估和理论分析报告,以验证所提出的方法的有效性。四个基准测试,无论是经典的和大规模的实验结果表明,我们的方法是能够实现新的国家的最先进的性能上的大多数评价。本文中使用的代码和数据集可在{ \it github.com/lijin118/ATM}获得。

英文摘要:

Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named Adversarial Tight Match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named Maximum Density Divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations. Codes and datasets used in this paper are available at {\it github.com/lijin118/ATM}.

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。

↑