无需搜索即可动态调整图像增强策略，提升模型泛化能力。
Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition
- 根据样本复杂度动态分配增强强度，实现个性化增强
- 在ImageNet上达到78.31%的Top-1准确率，逼近搜索型方法
- 兼容现有流程，无需调参，适合部署到新任务中
自动数据增强（AutoDA）对提升神经网络泛化能力至关重要。但主流方法面临两大挑战：搜索过程耗时过长，或因训练中策略适应不足导致性能不佳。为此，我们提出样本感知的RandAugment（SRA），一种非对称、无需搜索的AutoDA方法，可在保持简单实现的同时动态调整增强策略。SRA引入启发式评分模块，评估原始训练数据的复杂度，为每个样本定制增强方式。同时采用非对称增强策略以最大化评分模块潜力。在多个实验设置中，SRA缩小了搜索型与无搜索型AutoDA之间的性能差距，在ResNet-50下于ImageNet上取得78.31%的最高Top-1准确率。SRA表现出良好的现有增强流水线兼容性与跨任务泛化能力，无需超参数调优。基于SRA预训练的模型也显著提升了下游目标检测任务的识别性能。SRA为更简单、高效、实用的AutoDA设计提供了可行路径。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。