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

CAFT: Class Aware Frequency Transform for Reducing Domain Gap

Kumar, V and Srivastava, S and Lal, R and Chakraborty, A (2021) CAFT: Class Aware Frequency Transform for Reducing Domain Gap. In: 18th IEEE/CVF International Conference on Computer Vision Workshops, 11-17 Oct 2021, pp. 2525-2534.

[img] PDF
IEEE_ICCVW_2021.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: https://doi.org/10.1109/ICCVW54120.2021.00285


This work explores the usage of Fourier Transform for reducing the domain gap between the Source (e.g. Synthetic Image) and Target domain (e.g. Real Image) towards solving the Domain Adaptation problem. Most of the Unsupervised Domain Adaptation (UDA) algorithms reduce the global domain shift between labelled Source and unlabelled Target domain by matching the marginal distribution. UDA performance deteriorates for the cases where the domain gap between Source and Target is significant. To improve the overall performance of the existing UDA algorithms the proposed method attempts to bring the Source domain closer to the Target domain with the help of pseudo label based class consistent low-frequency swapping. This traditional image processing technique results in computational efficiency, especially compared to the state-of-the-art deep learning methods that use complex adversarial training. The proposed method Class Aware Frequency Transformation (CAFT1) can easily be plugged into any existing UDA algorithm to improve its performance. We evaluate CAFT on various domain adaptation datasets and algorithms and have achieved performance gains across all the popular benchmarks. © 2021 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.
Keywords: Benchmarking; Computer vision; Deep learning, Adaptation algorithms; Domain adaptation; Frequency transform; Global domain; Image domain; Matchings; Performance; Real images; Synthetic images; Target domain, Computational efficiency
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 01 Feb 2022 12:33
Last Modified: 01 Feb 2022 12:33
URI: http://eprints.iisc.ac.in/id/eprint/71123

Actions (login required)

View Item View Item