Selective mixing and voting network for semi-supervised domain generalization

Arfeen, A and Dutta, T and Biswas, S (2021) Selective mixing and voting network for semi-supervised domain generalization. In: 12th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2021, 20-22 Dec 2021, Virtual, Online.

PDF ICVGIP_2021.pdf - Published Version Restricted to Registered users only Download (683kB) | Request a copy

Abstract

Domain generalization (DG) addresses the problem of generalizing classification performance across any unknown domain, by leveraging training samples from multiple source domains. Currently, the training process of the state-of-the-art DG-methods is dependent on a large amount of labeled data. This restricts the application of the models in many real-world scenarios, where collecting and annotating a large dataset is an expensive and difficult task. Thus, in this paper, we address the problem of Semi-supervised Domain Generalization (SSDG), where the training set contains only a few labeled data, in addition to a large number of unlabeled data from multiple domains. This is relatively unexplored in literature and poses a considerable challenge to the state-of-the-art DG models, since their performance degrades under such condition. To address this scenario, we propose a novel Selective Mixing and Voting Network (SMV-Net), which effectively extracts useful knowledge from the set of unlabeled training data, available to the model. Specifically, we propose a mixing strategy on selected unlabeled samples on which the model is confident about their predicted class labels to achieve a domain-invariant representation of the data, which generalizes effectively across any unseen domain. Secondly, we also propose a voting module, which not only improves the generalization capability of the classifier, but can also comment on the prediction of the test samples, using references from a few labeled training examples, despite of their domain gap. Finally, we introduce a test-time mixing strategy to re-look at the top class-predictions and re-order them if required to further boost the classification performance. Extensive experiments on two popular DG-datasets demonstrate the usefulness of the proposed framework. © 2021 ACM.

Item Type:	Conference Paper
Publication:	ACM International Conference Proceeding Series
Publisher:	Association for Computing Machinery
Additional Information:	The copyright for this article belongs to Association for Computing Machinery
Keywords:	Large dataset; Supervised learning, Classification performance; Domain generalization; Generalisation; Labeled data; Mix-up strategy; Multiple source; Selective mixing; Semi-supervised; State of the art; Training sample, Mixing
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	20 Jan 2022 06:55
Last Modified:	20 Jan 2022 06:55
URI:	http://eprints.iisc.ac.in/id/eprint/70998

Actions (login required)

View Item