English

Spectral Wavelet Dropout: Regularization in the Wavelet Domain

Computer Vision and Pattern Recognition 2024-09-30 v1 Machine Learning

Abstract

Regularization techniques help prevent overfitting and therefore improve the ability of convolutional neural networks (CNNs) to generalize. One reason for overfitting is the complex co-adaptations among different parts of the network, which make the CNN dependent on their joint response rather than encouraging each part to learn a useful feature representation independently. Frequency domain manipulation is a powerful strategy for modifying data that has temporal and spatial coherence by utilizing frequency decomposition. This work introduces Spectral Wavelet Dropout (SWD), a novel regularization method that includes two variants: 1D-SWD and 2D-SWD. These variants improve CNN generalization by randomly dropping detailed frequency bands in the discrete wavelet decomposition of feature maps. Our approach distinguishes itself from the pre-existing Spectral "Fourier" Dropout (2D-SFD), which eliminates coefficients in the Fourier domain. Notably, SWD requires only a single hyperparameter, unlike the two required by SFD. We also extend the literature by implementing a one-dimensional version of Spectral "Fourier" Dropout (1D-SFD), setting the stage for a comprehensive comparison. Our evaluation shows that both 1D and 2D SWD variants have competitive performance on CIFAR-10/100 benchmarks relative to both 1D-SFD and 2D-SFD. Specifically, 1D-SWD has a significantly lower computational complexity compared to 1D/2D-SFD. In the Pascal VOC Object Detection benchmark, SWD variants surpass 1D-SFD and 2D-SFD in performance and demonstrate lower computational complexity during training.

Keywords

Cite

@article{arxiv.2409.18951,
  title  = {Spectral Wavelet Dropout: Regularization in the Wavelet Domain},
  author = {Rinor Cakaj and Jens Mehnert and Bin Yang},
  journal= {arXiv preprint arXiv:2409.18951},
  year   = {2024}
}

Comments

Accepted by The International Conference on Machine Learning and Applications (ICMLA) 2024

R2 v1 2026-06-28T18:59:50.394Z