Transfering Low-Frequency Features for Domain Adaptation
This addresses the problem of domain shift for computer vision applications, offering a plug-and-play solution that is incremental to existing methods.
The paper tackles domain adaptation in computer vision by proposing that low-frequency features are domain-invariant, introducing a low-frequency module (LFM) to extract these features, and shows it outperforms state-of-the-art methods in tasks like image classification and object detection.
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of different domains can be decomposed into the low-frequency component and high-frequency component. This paper proposes the assumption that low-frequency information is more domain-invariant while the high-frequency information contains domain-related information. Hence, we introduce an approach, named low-frequency module (LFM), to extract domain-invariant feature representations. The LFM is constructed with the digital Gaussian low-pass filter. Our method is easy to implement and introduces no extra hyperparameter. We design two effective ways to utilize the LFM for domain adaptation, and our method is complementary to other existing methods and formulated as a plug-and-play unit that can be combined with these methods. Experimental results demonstrate that our LFM outperforms state-of-the-art methods for various computer vision tasks, including image classification and object detection.