Rangwani, H and Jain, A and Aithal, SK and Babu, RV (2021) S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation. In: 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021, 11 -17 October 2021, Virtual, Online, pp. 7496-7505.
|
PDF
IEEE_ICCV_2021.pdf - Published Version Download (935kB) | Preview |
Abstract
Unsupervised domain adaptation (DA) methods have focused on achieving maximal performance through aligning features from source and target domains without using labeled data in the target domain. Whereas, in the real-world scenario's it might be feasible to get labels for a small proportion of target data. In these scenarios, it is important to select maximally-informative samples to label and find an effective way to combine them with the existing knowledge from source data. Towards achieving this, we propose S3VAADA which i) introduces a novel submodular criterion to select a maximally informative subset to label and ii) enhances a cluster-based DA procedure through novel improvements to effectively utilize all the available data for improving generalization on target. Our approach consistently outperforms the competing state-of-the-art approaches on datasets with varying degrees of domain shifts. The project page with additional details is available here: https://sites.google.com/iisc.ac.in/s3vaada-iccv2021/. © 2021 IEEE
| Item Type: | Conference Proceedings |
|---|---|
| Publication: | Proceedings of the IEEE International Conference on Computer Vision |
| Publisher: | Institute of Electrical and Electronics Engineers Inc. |
| Additional Information: | The copyright for this article belongs to author |
| Department/Centre: | Division of Electrical Sciences > Computer Science & Automation |
| Date Deposited: | 19 May 2022 06:51 |
| Last Modified: | 19 May 2022 06:51 |
| URI: | https://eprints.iisc.ac.in/id/eprint/71899 |
Actions (login required)
 |
View Item |
