arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.09693cs.LGcs.CVstat.ML
收藏

无监督领域自适应的贝叶斯不确定性匹配

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

Qiushi Academy for Advanced Studies, Zhejiang University(浙江大学求是高等研究院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);State University of New York at Buffalo(纽约州立大学布法罗分校);Zhejiang University School of Medicine(浙江大学医学院)

Jun Wen, Nenggan Zheng, Junsong Yuan, Zhefeng Gong, Changyou Chen

摘要:

领域自适应是一种重要的技术,用于减轻由领域移位引起的性能下降,当训练和测试数据来自不同的域时。由于目标域标签的不可用,大多数现有的深度自适应方法都集中在通过对输入特征进行深度变换来匹配边缘特征分布来减少域偏移。我们表明,域移位可能仍然存在通过标签分布偏移在分类器,从而恶化模型的性能。为了缓解这个问题,我们提出了一个近似的联合分布匹配方案,利用预测的不确定性。具体来说,我们使用贝叶斯神经网络来量化分类器的预测不确定性。通过对特征和标签(通过不确定性)进行分布匹配,有效地缓解了源数据和目标数据中的标签分布不匹配,鼓励分类器跨域产生一致的预测。我们还提出了一些技术来改进我们的方法,通过自适应重新加权领域自适应损失,以实现非平凡的分布匹配和稳定的训练。在三个流行的基准数据集上与最先进的无监督领域自适应方法的比较表明了我们的方法的优越性,特别是在减轻负迁移的有效性。

英文摘要:

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.

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。

↑