# Transfering Low-Frequency Features for Domain Adaptation

arXiv: https://arxiv.org/abs/2208.14706 · HTML: https://mlsanity.com/paper/2208.14706/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 31 Aug 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution](https://mlsanity.com/paper/1904.05049/) (2019)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [MST: Masked Self-Supervised Transformer for Visual Representation](https://mlsanity.com/paper/2106.05656/) (2021)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [UniVIP: A Unified Framework for Self-Supervised Visual Pre-training](https://mlsanity.com/paper/2203.06965/) (2022)

## Built on by (most cited first, 5 of 5)

- [Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging](https://mlsanity.com/paper/2503.22236/) (2025)
- [Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks](https://mlsanity.com/paper/2209.13948/) (2022)
- [Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2304.07031/) (2023)
- [Efficient Masked Autoencoders with Self-Consistency](https://mlsanity.com/paper/2302.14431/) (2023)
- [FreConv: Frequency Branch-and-Integration Convolutional Networks](https://mlsanity.com/paper/2304.04540/) (2023)

## Abstract (arXiv)

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.