# Hypernetwork-Based Augmentation

Source: [Hypernetwork-Based Augmentation](<https://www.sota2.com/research/paper/68fa6aef1e209131cea2b2a9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:50.089Z

Authors: Chih-Yang Chen, Che-Han Chang

Published: 2020-06-11T10:36:39.000Z

## Abstract

Data augmentation is an effective technique to improve the generalization of deep neural networks. Recently, AutoAugment proposed a well-designed search space and a search algorithm that automatically finds augmentation policies in a data-driven manner. However, AutoAugment is computationally intensive. In this paper, we propose an efficient gradient-based search algorithm, called Hypernetwork-Based Augmentation (HBA), which simultaneously learns model parameters and augmentation hyperparameters in a single training. Our HBA uses a hypernetwork to approximate a population-based training algorithm, which enables us to tune augmentation hyperparameters by gradient descent. Besides, we introduce a weight sharing strategy that simplifies our hypernetwork architecture and speeds up our search algorithm. We conduct experiments on CIFAR-10, CIFAR-100, SVHN, and ImageNet. Our results show that HBA is competitive to the state-of-the-art methods in terms of both search speed and accuracy.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.06320>)

[PDF](<https://arxiv.org/pdf/2006.06320.pdf>)