Improving semi-supervised domain adaptation using effective target selection and semantics

Singh, A and Doraiswamy, N and Takamuku, S and Bhalerao, M and Dutta, T and Biswas, S and Chepuri, A and Vengatesan, B and Natori, N (2021) Improving semi-supervised domain adaptation using effective target selection and semantics. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,, 19-25 jun 2021, pp. 2703-2712.

PDF IEEE_CVPRW _2021.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Recently, semi-supervised domain adaptation (SSDA) approaches have shown impressive performance for the domain adaptation task. They effectively utilize few labeled target samples along with the unlabeled data to account for the distribution shift across the source and target domains. In this work, we make three-fold contributions, concentrating on the role of target samples and semantics for the SSDA task. First, we observe that choosing a few, but an equal number of labeled samples from each class in the target domain requires a significant amount of manual effort. To address this, we propose an active learning-based framework by modeling both the sample diversity and the classifier uncertainty. By utilizing k-means initialized cluster centers for picking a small pool of diverse unlabeled target samples, we compute a novel classifier adaptation uncertainty term to select the most effective samples from this pool, which are queried to obtain their true labels from an oracle. Second, we propose to weigh the hard target samples more, without explicitly using their predicted, possibly incorrect labels, which guides the adaptation process. Third, we note that irrespective of the domain shift, the semantics of the classes remain unchanged, so they can be effectively utilized for this task. We show that initializing the class-representations or prototypes with the class-semantics helps in bridging the domain gap significantly. These along with adversarially learnt entropy objective results in a novel framework, termed STar (Select TARgets), which sets a new state-of-the-art for the SSDA task. © 2021 IEEE.

Item Type:	Conference Paper
Publication:	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher:	IEEE Computer Society
Additional Information:	The copyright for this article belongs to IEEE Computer Society
Keywords:	Computer vision; K-means clustering; Uncertainty analysis, Active Learning; Domain adaptation; K-means; Performance; Semi-supervised; Target domain; Targets selection; Three folds; Uncertainty; Unlabeled data, Semantics
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	07 Dec 2021 10:23
Last Modified:	07 Dec 2021 10:23
URI:	http://eprints.iisc.ac.in/id/eprint/70387

Actions (login required)

View Item