Authors:
Kyungsik Lee
;
Youngmi Jun
;
EunJi Kim
;
Suhyun Kim
;
Seong Hwang
and
Jonghyun Choi
Affiliation:
Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea
Keyword(s):
Unsupervised Domain Adaptation, Unlabeled Target Domain, Pseudo labels, K-means Clustering, Centroids.
Abstract:
In unsupervised domain adaptation (UDA) literature, there exists an array of techniques to derive domain adaptive features. Among them, a particularly successful family of approaches of pseudo-labeling the unlabeled target data has shown promising results. Yet, the majority of the existing methods primarily focus on leveraging only the target domain knowledge for pseudo-labeling while insufficiently considering the source domain knowledge. Here, we hypothesize that quality pseudo labels obtained via classical K-means clustering considering both the source and target domains bring simple yet significant benefits. In particular, we propose to assign pseudo labels to the target domain’s instances better aligned with the source domain labels by a simple method that modifies K-means clustering by emphasizing the strengthened notion of centroids, namely, Kore Initial Clustering (KIC). The proposed KIC is readily utilizable with a wide array of UDA models, consistently improving the UDA per
formance on multiple UDA datasets including Office-Home and Office-31, demonstrating the efficacy of pseudo labels in UDA.
(More)