# Harmonic Networks with Limited Training Samples

arXiv: https://arxiv.org/abs/1905.00135 · HTML: https://mlsanity.com/paper/1905.00135/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification](https://mlsanity.com/paper/2108.13122/) (2021)
- [Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification](https://mlsanity.com/paper/2209.13233/) (2022)
- [Image Classification with Small Datasets: Overview and Benchmark](https://mlsanity.com/paper/2212.12478/) (2022)
- [Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models](https://mlsanity.com/paper/2106.01440/) (2021)
- [No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets](https://mlsanity.com/paper/2309.01694/) (2023)
- [Scale-invariant Gaussian derivative residual networks](https://mlsanity.com/paper/2603.02843/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we examine the performance of harmonic networks in limited training data scenario. We validate experimentally that its performance compares well against scattering networks that use wavelets as preset filters.