Sanyal, S and Asokan, AR and Bhambri, S and Kulkarni, A and Kundu, JN and Babu, RV (2023) Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation. In: UNSPECIFIED, pp. 18882-18891.
![]() |
PDF
Pro_iee_int_con_com_vis_2023 - Published Version Restricted to Registered users only Download (2MB) | Request a copy |
Abstract
Conventional Domain Adaptation (DA) methods aim to learn domain-invariant feature representations to improve the target adaptation performance. However, we motivate that domain-specificity is equally important since in-domain trained models hold crucial domain-specific properties that are beneficial for adaptation. Hence, we propose to build a framework that supports disentanglement and learning of domain-specific factors and task-specific factors in a unified model. Motivated by the success of vision transformers in several multi-modal vision problems, we find that queries could be leveraged to extract the domain-specific factors. Hence, we propose a novel Domain-Specificity inducing Transformer (DSiT) framework 1 for disentangling and learning both domain-specific and task-specific factors. To achieve disentanglement, we propose to construct novel Domain-Representative Inputs (DRI) with domain-specific information to train a domain classifier with a novel domain token. We are the first to utilize vision transformers for domain adaptation in a privacy-oriented source-free setting, and our approach achieves state-of-the-art performance on single-source, multi-source, and multi-target benchmarks. © 2023 IEEE.
Item Type: | Conference Paper |
---|---|
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 Institute of Electrical and Electronics Engineers Inc. |
Department/Centre: | Others |
Date Deposited: | 16 May 2024 09:40 |
Last Modified: | 16 May 2024 09:40 |
URI: | https://eprints.iisc.ac.in/id/eprint/84525 |
Actions (login required)
![]() |
View Item |