论文标题
开放设定的假设转移具有语义一致性
Open-Set Hypothesis Transfer with Semantic Consistency
论文作者
论文摘要
无监督的开放式域适应性（UODA）是一个现实的问题，其中未标记的目标数据包含未知类别。先前的方法依靠源和目标域数据的共存来执行域对齐，这在由于隐私问题而受到限制时极大地限制了其应用程序。本文解决了UODA的挑战性假设转移设置，在该目标域对源域的数据不再可用。我们介绍了一种侧重于目标数据转换下的语义一致性的方法，这很少受到以前的域适应方法的理解。具体而言，我们的模型首先发现了自信的预测，并使用伪标签执行分类。然后，我们强制执行该模型以在语义上相似的输入上输出一致和确定的预测。结果，可以将未标记的数据分为歧视类别，与源类或未知类别一致。实验结果表明，我们的模型在UODA基准测试中优于最先进的方法。
Unsupervised open-set domain adaptation (UODA) is a realistic problem where unlabeled target data contain unknown classes. Prior methods rely on the coexistence of both source and target domain data to perform domain alignment, which greatly limits their applications when source domain data are restricted due to privacy concerns. This paper addresses the challenging hypothesis transfer setting for UODA, where data from source domain are no longer available during adaptation on target domain. We introduce a method that focuses on the semantic consistency under transformation of target data, which is rarely appreciated by previous domain adaptation methods. Specifically, our model first discovers confident predictions and performs classification with pseudo-labels. Then we enforce the model to output consistent and definite predictions on semantically similar inputs. As a result, unlabeled data can be classified into discriminative classes coincided with either source classes or unknown classes. Experimental results show that our model outperforms state-of-the-art methods on UODA benchmarks.
