Kumar, V and Lal, R and Patil, H and Chakraborty, A (2023) CoNMix for Source-free Single and Multi-target Domain Adaptation. In: 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, 3 - 7 January 2023, Waikoloa, pp. 4167-4177.
|
PDF
wacv_2023.pdf - Published Version Download (3MB) | Preview |
Abstract
This work introduces the novel task of Source-free Multi-target Domain Adaptation and proposes adaptation framework comprising of Consistency with Nuclear-Norm Maximization and MixUp knowledge distillation (CoNMix) as a solution to this problem. The main motive of this work is to solve for Single and Multi target Domain Adaptation (SMTDA) for the source-free paradigm, which enforces a constraint where the labeled source data is not available during target adaptation due to various privacy-related restrictions on data sharing. The source-free approach leverages target pseudo labels, which can be noisy, to improve the target adaptation. We introduce consistency between label preserving augmentations and utilize pseudo label refinement methods to reduce noisy pseudo labels. Further, we propose novel MixUp Knowledge Distillation (MKD) for better generalization on multiple target domains using various source-free STDA models. We also show that the Vision Transformer (VT) backbone gives better feature representation with improved domain transferability and class discriminability. Our proposed framework achieves the state-of-the-art (SOTA) results in various paradigms of source-free STDA and MTDA settings on popular domain adaptation datasets like Office-Home, Office-Caltech, and DomainNet. Project Page: https://sites.google.com/view/conmix-vcl © 2023 IEEE.
Item Type: | Conference Paper |
---|---|
Publication: | Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023 |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Additional Information: | The copyright for this article belongs to the Authors. |
Keywords: | Computer vision; Distillation; Learning algorithms, Algorithm: machine learning architecture; And algorithm (including transfer); Domain adaptation; Formulation; Learning architectures; Machine-learning; Multi-targets; Novel task; Target domain; Vision + language and/or other modality, Machine learning |
Department/Centre: | Division of Interdisciplinary Sciences > Computational and Data Sciences |
Date Deposited: | 15 Mar 2023 06:03 |
Last Modified: | 15 Mar 2023 06:03 |
URI: | https://eprints.iisc.ac.in/id/eprint/80988 |
Actions (login required)
View Item |