Guardado en:
Detalles Bibliográficos
Autores principales: Xiao, Anqi, Yu, Weichen, Yu, Hongyuan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.08004
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911101592010752
author Xiao, Anqi
Yu, Weichen
Yu, Hongyuan
author_facet Xiao, Anqi
Yu, Weichen
Yu, Hongyuan
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2508_08004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition
Xiao, Anqi
Yu, Weichen
Yu, Hongyuan
Computer Vision and Pattern Recognition
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
title Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.08004