Differentiable RandAugment: Learning Selecting Weights and Magnitude Distributions of Image Transformations

doi:10.1109/TIP.2023.3265266

	Differentiable RandAugment: Learning Selecting Weights and Magnitude Distributions of Image Transformations
	Xiao, Anqi 1; Shen, Biluo1 ; Tian, Jie 1,2,3; Hu, Zhenhua1
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2023
卷号	32 页码:2413-2427
通讯作者	Tian, Jie(tian@ieee.org)
摘要	Automatic data augmentation is a technique to automatically search for strategies for image transformations, which can improve the performance of different vision tasks. RandAugment (RA), one of the most widely used automatic data augmentations, achieves great success in different scales of models and datasets. However, RA randomly selects transformations with equivalent probabilities and applies a single magnitude for all transformations, which is suboptimal for different models and datasets. In this paper, we develop Differentiable RandAugment (DRA) to learn selecting weights and magnitudes of transformations for RA. The magnitude of each transformation is modeled following a normal distribution with both learnable mean and standard deviation. We also introduce the gradient of transformations to reduce the bias in gradient estimation and KL divergence as part of the loss to reduce the optimization gap. Experiments on CIFAR-10/100 and ImageNet demonstrate the efficiency and effectiveness of DRA. Searching for only 0.95 GPU hours on ImageNet, DRA can reach a Top-1 accuracy of 78.19% with ResNet-50, which outperforms RA by 0.28% under the same settings. Transfer learning on object detection also demonstrates the power of DRA. The proposed DRA is one of the few that surpasses RA on ImageNet and has great potential to be integrated into modern training pipelines to achieve state-of-the-art performance. Our code will be made publicly available for out-of-the-box use.
关键词	Task analysis Training Data models Costs Optimization Search problems Upper bound Data augmentation automated machine learning differentiable optimization random augmentation
DOI	10.1109/TIP.2023.3265266
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[92059207] ; National Natural Science Foundation of China (NSFC)[62027901] ; National Natural Science Foundation of China (NSFC)[81930053] ; National Natural Science Foundation of China (NSFC)[81227901] ; Chinese Academy of Sciences (CAS) Youth Interdisciplinary[JCTD-2021-08] ; Zhuhai High-Level Health Personnel Team Project[HLHPTP201703] ; Cloud TensorProcessing Unit (TPUs) from Google's TPU Research Cloud (TRC)
项目资助者	National Natural Science Foundation of China (NSFC) ; Chinese Academy of Sciences (CAS) Youth Interdisciplinary ; Zhuhai High-Level Health Personnel Team Project ; Cloud TensorProcessing Unit (TPUs) from Google's TPU Research Cloud (TRC)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000981890900002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53264
专题	中国科学院分子影像重点实验室
通讯作者	Tian, Jie
作者单位	1.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China 2.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Engn Med, Beijing 100191, Peoples R China 3.Xidian Univ, Engn Res Ctr Mol & Neuro Imaging, Sch Life Sci & Technol, Minist Educ, Xian 710071, Peoples R China
第一作者单位	中国科学院分子影像重点实验室
通讯作者单位	中国科学院分子影像重点实验室
推荐引用方式 GB/T 7714	Xiao, Anqi,Shen, Biluo,Tian, Jie,et al. Differentiable RandAugment: Learning Selecting Weights and Magnitude Distributions of Image Transformations[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:2413-2427.
APA	Xiao, Anqi,Shen, Biluo,Tian, Jie,&Hu, Zhenhua.(2023).Differentiable RandAugment: Learning Selecting Weights and Magnitude Distributions of Image Transformations.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,2413-2427.
MLA	Xiao, Anqi,et al."Differentiable RandAugment: Learning Selecting Weights and Magnitude Distributions of Image Transformations".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):2413-2427.