# Feature transforms for image data augmentation

arXiv: https://arxiv.org/abs/2201.09700 · HTML: https://mlsanity.com/paper/2201.09700/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 62 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [Data Augmentation by Pairing Samples for Images Classification](https://mlsanity.com/paper/1801.02929/) (2018)
- [Improved Mixed-Example Data Augmentation](https://mlsanity.com/paper/1805.11272/) (2018)
- [Improving Deep Learning using Generic Data Augmentation](https://mlsanity.com/paper/1708.06020/) (2017)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [PatchShuffle Regularization](https://mlsanity.com/paper/1707.07103/) (2017)
- [DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization](https://mlsanity.com/paper/2103.14545/) (2021)
- [Tree Species Identification from Bark Images Using Convolutional Neural Networks](https://mlsanity.com/paper/1803.00949/) (2018)
- [Computer-aided diagnosis in histopathological images of the endometrium using a convolutional neural network and attention mechanisms](https://mlsanity.com/paper/1904.10626/) (2019)
- [Deep Features for training Support Vector Machine](https://mlsanity.com/paper/2104.03488/) (2021)
- [General Purpose (GenP) Bioimage Ensemble of Handcrafted and Learned Features with Data Augmentation](https://mlsanity.com/paper/1904.08084/) (2019)

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

- [Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga](https://mlsanity.com/paper/2410.05935/) (2024)
- [Topology-Preserving Scaling in Data Augmentation](https://mlsanity.com/paper/2411.19512/) (2024)
- [LightTeaNet: A Weakly Supervised Lightweight CNN for Multi-Label Tea Leaf Disease Detection and Localization](https://mlsanity.com/paper/2608.14178/) (2026)

## Abstract (arXiv)

A problem with Convolutional Neural Networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many methods have been proposed to overcome this shortcoming with CNNs. In cases where additional samples cannot easily be collected, a common approach is to generate more data points from existing data using an augmentation technique. In image classification, many augmentation approaches utilize simple image manipulation algorithms. In this work, we build ensembles on the data level by adding images generated by combining fourteen augmentation approaches, three of which are proposed here for the first time. These novel methods are based on the Fourier Transform (FT), the Radon Transform (RT) and the Discrete Cosine Transform (DCT). Pretrained ResNet50 networks are finetuned on training sets that include images derived from each augmentation method. These networks and several fusions are evaluated and compared across eleven benchmarks. Results show that building ensembles on the data level by combining different data augmentation methods produce classifiers that not only compete competitively against the state-of-the-art but often surpass the best approaches reported in the literature.