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

TL;DR

Sample-aware RandAugment (SRA) introduces a simple, search-free data augmentation method that dynamically adapts to individual samples, improving image recognition accuracy and compatibility across tasks without extensive tuning.

Contribution

SRA is a novel, search-free AutoDA approach that uses a heuristic scoring module and asymmetric augmentation to enhance performance and practicality.

Findings

Achieves 78.31% Top-1 accuracy on ImageNet with ResNet-50.

Narrowed performance gap between search-based and search-free AutoDA methods.

Demonstrates strong generalization and compatibility across tasks.

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