# RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios

Source: [RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios](<https://www.sota2.com/research/paper/68fa71461e209131cea504e2>)

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

Data updated: 2025-10-26T02:02:40.220Z

Authors: Swarna Kamlam Ravindran, Carlo Tomasi

Published: 2023-11-25T18:07:20.000Z

## Abstract

The high costs of annotating large datasets suggests a need for effectively training CNNs with limited data, and data augmentation is a promising direction. We study foundational augmentation techniques, including Mixed Sample Data Augmentations (MSDAs) and a no-parameter variant of RandAugment termed Preset-RandAugment, in the fully supervised scenario. We observe that Preset-RandAugment excels in limited-data contexts while MSDAs are moderately effective. We show that low-level feature transforms play a pivotal role in this performance difference, postulate a new property of augmentations related to their data efficiency, and propose new ways to measure the diversity and realism of augmentations. Building on these insights, we introduce a novel augmentation technique called RandMSAugment that integrates complementary strengths of existing methods. RandMSAugment significantly outperforms the competition on CIFAR-100, STL-10, and Tiny-Imagenet. With very small training sets (4, 25, 100 samples/class), RandMSAugment achieves compelling performance gains between 4.1% and 6.75%. Even with more training data (500 samples/class) we improve performance by 1.03% to 2.47%. RandMSAugment does not require hyperparameter tuning, extra validation data, or cumbersome optimizations.

## 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/2311.16508>)

[PDF](<https://arxiv.org/pdf/2311.16508.pdf>)
