Frequency learning for image classification
This addresses the problem of enhancing image classification performance for computer vision applications by incorporating frequency domain analysis, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles the problem of improving image classification by exploring frequency domain information, proposing trainable frequency filters and a slicing procedure to learn global and local features from Fourier transforms. The method proved competitive with well-known deep neural network architectures while being simpler and lightweight.
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.