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

Improving Domain Adaptation Through Class Aware Frequency Transformation

Kumar, V and Patil, H and Lal, R and Chakraborty, A (2023) Improving Domain Adaptation Through Class Aware Frequency Transformation. In: International Journal of Computer Vision .

[img] PDF
int_jou_com_2023.pdf - Published Version
Restricted to Registered users only

Download (3MB) | Request a copy
Official URL: https://doi.org/10.1007/s11263-023-01810-0


In this work, we explore the usage of the frequency transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the domain adaptation task. Most of the unsupervised domain adaptation (UDA) algorithms focus on reducing the global domain shift between labelled source and unlabelled target domains by matching the marginal distributions under a small domain gap assumption. UDA performance degrades for the cases where the domain gap between source and target distribution is large. In order to bring the source and the target domains closer, we propose a novel approach based on traditional image processing technique Class Aware Frequency Transformation (CAFT) that utilizes pseudo label based class consistent low-frequency swapping for improving the overall performance of the existing UDA algorithms. The proposed approach, when compared with the state-of-the-art deep learning based methods, is computationally more efficient and can easily be plugged into any existing UDA algorithm to improve its performance. Additionally, we introduce a novel approach based on absolute difference of top-2 class prediction probabilities for filtering target pseudo labels into clean and noisy sets. Samples with clean pseudo labels can be used to improve the performance of unsupervised learning algorithms. We name the overall framework as CAFT++. We evaluate the same on the top of different UDA algorithms across many public domain adaptation datasets. Our extensive experiments indicate that CAFT++ is able to achieve significant performance gains across all the popular benchmarks.

Item Type: Journal Article
Publication: International Journal of Computer Vision
Publisher: Springer
Additional Information: The copyright for this article belongs to the Springer.
Keywords: Frequency transformation; Gaussian mixture model; Pseudo label; Unsupervised domain adaptation.
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 24 Jul 2023 11:45
Last Modified: 24 Jul 2023 11:45
URI: https://eprints.iisc.ac.in/id/eprint/82622

Actions (login required)

View Item View Item