# Frequency learning for image classification

arXiv: https://arxiv.org/abs/2006.15476 · HTML: https://mlsanity.com/paper/2006.15476/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2020.

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

- [FFCNet: Fourier Transform-Based Frequency Learning and Complex Convolutional Network for Colon Disease Classification](https://mlsanity.com/paper/2207.01287/) (2022)
- [An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training](https://mlsanity.com/paper/2206.03359/) (2022)
- [Joint Learning of Frequency and Spatial Domains for Dense Predictions](https://mlsanity.com/paper/2202.08991/) (2022)
- [Development of a Dual-Input Neural Model for Detecting AI-Generated Imagery](https://mlsanity.com/paper/2406.13688/) (2024)
- [Spectral Phase Encoding for Quantum Kernel Methods](https://mlsanity.com/paper/2602.19644/) (2026)

## Abstract (arXiv)

Machine learning applied to computer vision and signal processing is achieving results comparable to the human brain on specific tasks due to the great improvements brought by the deep neural networks (DNN). The majority of state-of-the-art architectures nowadays are DNN related, but only a few explore the frequency domain to extract useful information and improve the results, like in the image processing field. In this context, this paper presents a new approach for exploring the Fourier transform of the input images, which is composed of trainable frequency filters that boost discriminative components in the spectrum. Additionally, we propose a slicing procedure to allow the network to learn both global and local features from the frequency-domain representations of the image blocks. The proposed method proved to be competitive with respect to well-known DNN architectures in the selected experiments, with the advantage of being a simpler and lightweight model. This work also raises the discussion on how the state-of-the-art DNNs architectures can exploit not only spatial features, but also the frequency, in order to improve its performance when solving real world problems.