# Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition

Source: [Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition](<https://www.sota2.com/research/paper/68fa7a831e209131cea83a0a>)

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

Data updated: 2025-10-26T05:22:00.744Z

Authors: Anqi Xiao, Weichen Yu, Hongyuan Yu

Published: 2025-08-11T14:09:01.000Z

## Abstract

Automatic data augmentation (AutoDA) plays an important role in enhancing the generalization of neural networks. However, mainstream AutoDA methods often encounter two challenges: either the search process is excessively time-consuming, hindering practical application, or the performance is suboptimal due to insufficient policy adaptation during training. To address these issues, we propose Sample-aware RandAugment (SRA), an asymmetric, search-free AutoDA method that dynamically adjusts augmentation policies while maintaining straightforward implementation. SRA incorporates a heuristic scoring module that evaluates the complexity of the original training data, enabling the application of tailored augmentations for each sample. Additionally, an asymmetric augmentation strategy is employed to maximize the potential of this scoring module. In multiple experimental settings, SRA narrows the performance gap between search-based and search-free AutoDA methods, achieving a state-of-the-art Top-1 accuracy of 78.31\\% on ImageNet with ResNet-50. Notably, SRA demonstrates good compatibility with existing augmentation pipelines and solid generalization across new tasks, without requiring hyperparameter tuning. The pretrained models leveraging SRA also enhance recognition in downstream object detection tasks. SRA represents a promising step towards simpler, more effective, and practical AutoDA designs applicable to a variety of future tasks. Our code is available at \\href{https://github.com/ainieli/Sample-awareRandAugment}{https://github.com/ainieli/Sample-awareRandAugment

## 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.

- [Fossil fuel carbon emission prediction on Global fossil fuel carbon emission dataset](<https://www.sota2.com/research/sota/fossil-fuel-carbon-emission-prediction-on-global-fossil-fuel-carbon-emission-dataset.md>): Fossil fuel carbon emission prediction; Global fossil fuel carbon emission dataset; R2 (log): 0.904.

- [Fine-grained Image Classification on Stanford Dogs (test)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-stanford-dogs-test.md>): Fine-grained Image Classification; Stanford Dogs (test); Accuracy: 66.26.

- [Fine-grained Image Classification on CUB200 2011 (test)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub200-2011-test.md>): Fine-grained Image Classification; CUB200 2011 (test); Accuracy: 66.53.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.08004>)

[PDF](<https://arxiv.org/pdf/2508.08004.pdf>)
