论文标题
关于开放式域适应的图像旋转的有效性
On the Effectiveness of Image Rotation for Open Set Domain Adaptation
论文作者
论文摘要
打开的设置域改编（OSDA）桥接标记的源域和未标记的目标域之间的域间隙，同时还拒绝源中不存在的目标类。为了避免负转移，可以通过首先分离已知/未知目标样本，然后将已知目标样本与源数据对齐。我们提出了一种新的方法，可以使用自我监督的旋转识别任务来解决这两个问题。此外，我们通过一个新的开放式度量标准评估了性能，该指标能够正确地平衡认识已知类别并拒绝未知样本的贡献。与标准Office-31和Office-home基准上现有的OSDA方法进行的比较实验表明：（i）我们的方法优于其竞争对手，（ii）该领域的可重复性是解决问题的至关重要问题，（iii）我们的指标提供了一个可靠的工具，可以允许公平的开放设置评估。
Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source. To avoid negative transfer, OSDA can be tackled by first separating the known/unknown target samples and then aligning known target samples with the source data. We propose a novel method to addresses both these problems using the self-supervised task of rotation recognition. Moreover, we assess the performance with a new open set metric that properly balances the contribution of recognizing the known classes and rejecting the unknown samples. Comparative experiments with existing OSDA methods on the standard Office-31 and Office-Home benchmarks show that: (i) our method outperforms its competitors, (ii) reproducibility for this field is a crucial issue to tackle, (iii) our metric provides a reliable tool to allow fair open set evaluation.
