ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Universal Source-Free Domain Adaptation

Nath Kundu, J and Venkat, N and Rahul, MV and Venkatesh Babu, R (2020) Universal Source-Free Domain Adaptation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 14 - 19 June 2020, Virtual, Online, pp. 4543-4552.

[img] PDF
cvpr_2020.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: https://doi.org/10.1109/CVPR42600.2020.00460


There is a strong incentive to develop versatile learning techniques that can transfer the knowledge of class-separability from a labeled source domain to an unlabeled target domain in the presence of a domain-shift. Existing domain adaptation (DA) approaches are not equipped for practical DA scenarios as a result of their reliance on the knowledge of source-Target label-set relationship (e.g. Closed-set, Open-set or Partial DA). Furthermore, almost all prior unsupervised DA works require coexistence of source and target samples even during deployment, making them unsuitable for real-Time adaptation. Devoid of such impractical assumptions, we propose a novel two-stage learning process. 1) In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift. To achieve this, we enhance the model's ability to reject out-of-source distribution samples by leveraging the available source data, in a novel generative classifier framework. 2) In the Deployment stage, the goal is to design a unified adaptation algorithm capable of operating across a wide range of category-gaps, with no access to the previously seen source samples. To this end, in contrast to the usage of complex adversarial training regimes, we define a simple yet effective source-free adaptation objective by utilizing a novel instance-level weighting mechanism, named as Source Similarity Metric (SSM). A thorough evaluation shows the practical usability of the proposed learning framework with superior DA performance even over state-of-The-Art source-dependent approaches. © 2020 IEEE.

Item Type: Conference Paper
Publication: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher: IEEE Computer Society
Additional Information: The copyright for this article belongs to IEEE Computer Society.
Keywords: Learning systems, Adaptation algorithms; Class separability; Generative classifiers; Learning frameworks; Learning techniques; Real-time adaptation; Similarity metrics; Source distribution, Pattern recognition
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 08 Feb 2023 03:45
Last Modified: 08 Feb 2023 03:45
URI: https://eprints.iisc.ac.in/id/eprint/80014

Actions (login required)

View Item View Item