# Regularization of Deep Neural Networks with Spectral Dropout

arXiv: https://arxiv.org/abs/1711.08591 · HTML: https://mlsanity.com/paper/1711.08591/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2017.

## Built on by (most cited first, 14 of 14)

- [Fast-FNet: Accelerating Transformer Encoder Models via Efficient Fourier Layers](https://mlsanity.com/paper/2209.12816/) (2022)
- [MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment](https://mlsanity.com/paper/2508.13768/) (2025)
- [A Survey on Dropout Methods and Experimental Verification in Recommendation](https://mlsanity.com/paper/2204.02027/) (2022)
- [Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout](https://mlsanity.com/paper/2501.11258/) (2025)
- [Frequency Dropout: Feature-Level Regularization via Randomized Filtering](https://mlsanity.com/paper/2209.09844/) (2022)
- [Dropout Drops Double Descent](https://mlsanity.com/paper/2305.16179/) (2023)
- [Spectral Batch Normalization: Normalization in the Frequency Domain](https://mlsanity.com/paper/2306.16999/) (2023)
- [WV-Net: A foundation model for SAR WV-mode satellite imagery trained using contrastive self-supervised learning on 10 million images](https://mlsanity.com/paper/2406.18765/) (2024)
- [Dropout Neural Network Training Viewed from a Percolation Perspective](https://mlsanity.com/paper/2512.13853/) (2025)
- [Deep Learning with Kernel Flow Regularization for Time Series Forecasting](https://mlsanity.com/paper/2109.11649/) (2021)
- [Adaptive Low-Rank Regularization with Damping Sequences to Restrict Lazy Weights in Deep Networks](https://mlsanity.com/paper/2106.09677/) (2021)
- [Graph Enabled Cross-Domain Knowledge Transfer](https://mlsanity.com/paper/2304.03452/) (2023)
- [R-Block: Regularized Block of Dropout for convolutional networks](https://mlsanity.com/paper/2307.15150/) (2023)
- [Spectral Wavelet Dropout: Regularization in the Wavelet Domain](https://mlsanity.com/paper/2409.18951/) (2024)

## Abstract (arXiv)

The big breakthrough on the ImageNet challenge in 2012 was partially due to the `dropout' technique used to avoid overfitting. Here, we introduce a new approach called `Spectral Dropout' to improve the generalization ability of deep neural networks. We cast the proposed approach in the form of regular Convolutional Neural Network (CNN) weight layers using a decorrelation transform with fixed basis functions. Our spectral dropout method prevents overfitting by eliminating weak and `noisy' Fourier domain coefficients of the neural network activations, leading to remarkably better results than the current regularization methods. Furthermore, the proposed is very efficient due to the fixed basis functions used for spectral transformation. In particular, compared to Dropout and Drop-Connect, our method significantly speeds up the network convergence rate during the training process (roughly x2), with considerably higher neuron pruning rates (an increase of ~ 30%). We demonstrate that the spectral dropout can also be used in conjunction with other regularization approaches resulting in additional performance gains.