# SpecNet: Spectral Domain Convolutional Neural Network

arXiv: https://arxiv.org/abs/1905.10915 · HTML: https://mlsanity.com/paper/1905.10915/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 3 of 3)

- [As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain](https://mlsanity.com/paper/2307.10001/) (2023)
- [Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks](https://mlsanity.com/paper/2102.13323/) (2021)
- [SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning](https://mlsanity.com/paper/2110.10842/) (2021)

## Abstract (arXiv)

The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with increasing depth of the network, which is a major constraint for efficient network training on modern GPUs with limited memory, embedded systems, and mobile devices. Several studies show that the feature maps (as generated after the convolutional layers) are the main bottleneck in this memory problem. Often, these feature maps mimic natural photographs in the sense that their energy is concentrated in the spectral domain. Although embedding CNN architectures in the spectral domain is widely exploited to accelerate the training process, we demonstrate that it is also possible to use the spectral domain to reduce the memory footprint, a method we call Spectral Domain Convolutional Neural Network (SpecNet) that performs both the convolution and the activation operations in the spectral domain. The performance of SpecNet is evaluated on three competitive object recognition benchmark tasks (CIFAR-10, SVHN, and ImageNet), and compared with several state-of-the-art implementations. Overall, SpecNet is able to reduce memory consumption by about 60% without significant loss of performance for all tested networks.