# FcaNet: Frequency Channel Attention Networks

arXiv: https://arxiv.org/abs/2012.11879 · HTML: https://mlsanity.com/paper/2012.11879/

## Key facts

- Cited by 179 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 30 of 179)

- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Diffusion Probabilistic Model Made Slim](https://mlsanity.com/paper/2211.17106/) (2022)
- [Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition](https://mlsanity.com/paper/2109.07270/) (2021)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [Frequency-Spatial Entanglement Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2409.01686/) (2024)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [A Survey on Deep Learning based Time Series Analysis with Frequency Transformation](https://mlsanity.com/paper/2302.02173/) (2023)
- [MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection](https://mlsanity.com/paper/2403.19888/) (2024)
- [Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2308.05493/) (2023)
- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2112.03587/) (2021)
- [Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention](https://mlsanity.com/paper/2405.06284/) (2024)
- [Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution](https://mlsanity.com/paper/2208.03012/) (2022)
- [Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring](https://mlsanity.com/paper/2401.00027/) (2023)
- [From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective](https://mlsanity.com/paper/2503.13165/) (2025)
- [Global Spectral Filter Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2210.05567/) (2022)
- [HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection](https://mlsanity.com/paper/2412.10116/) (2024)
- [LoFormer: Local Frequency Transformer for Image Deblurring](https://mlsanity.com/paper/2407.16993/) (2024)
- [Frequency Dynamic Convolution for Dense Image Prediction](https://mlsanity.com/paper/2503.18783/) (2025)
- [Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization](https://mlsanity.com/paper/2507.15765/) (2025)
- [NTIRE 2021 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2105.03072/) (2021)
- [PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection](https://mlsanity.com/paper/2211.10763/) (2022)
- [EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network](https://mlsanity.com/paper/2105.14447/) (2021)
- [Frequency-Guided Spatial Adaptation for Camouflaged Object Detection](https://mlsanity.com/paper/2409.12421/) (2024)
- [Learning to Distill Global Representation for Sparse-View CT](https://mlsanity.com/paper/2308.08463/) (2023)
- [Image Quality-aware Diagnosis via Meta-knowledge Co-embedding](https://mlsanity.com/paper/2303.15038/) (2023)
- [Spectral Normalization and Dual Contrastive Regularization for Image-to-Image Translation](https://mlsanity.com/paper/2304.11319/) (2023)
- [Multi-spectral Class Center Network for Face Manipulation Detection and Localization](https://mlsanity.com/paper/2305.10794/) (2023)
- [EEG motor imagery decoding: A framework for comparative analysis with channel attention mechanisms](https://mlsanity.com/paper/2310.11198/) (2023)

## Abstract (arXiv)

Attention mechanism, especially channel attention, has gained great success in the computer vision field. Many works focus on how to design efficient channel attention mechanisms while ignoring a fundamental problem, i.e., channel attention mechanism uses scalar to represent channel, which is difficult due to massive information loss. In this work, we start from a different view and regard the channel representation problem as a compression process using frequency analysis. Based on the frequency analysis, we mathematically prove that the conventional global average pooling is a special case of the feature decomposition in the frequency domain. With the proof, we naturally generalize the compression of the channel attention mechanism in the frequency domain and propose our method with multi-spectral channel attention, termed as FcaNet. FcaNet is simple but effective. We can change a few lines of code in the calculation to implement our method within existing channel attention methods. Moreover, the proposed method achieves state-of-the-art results compared with other channel attention methods on image classification, object detection, and instance segmentation tasks. Our method could consistently outperform the baseline SENet, with the same number of parameters and the same computational cost. Our code and models will are publicly available at https://github.com/cfzd/FcaNet.