Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (11): 2980-2995.DOI: 10.3778/j.issn.1673-9418.2311022

• Graphics·Image • Previous Articles     Next Articles

Image Data Augmentation Method for Random Channel Perturbation

JIANG Wentao, LIU Yuwei, ZHANG Shengchong   

  1. 1. School of Software,Liaoning Technical University, Huludao, Liaoning 125105, China
    2. Key Laboratory of Optoelectronic Information Control and Security Technology, Tianjin 300308, China
  • Online:2024-11-01 Published:2024-10-31

随机通道扰动的图像数据增强方法

姜文涛,刘玉薇,张晟翀   

  1. 1. 辽宁工程技术大学 软件学院,辽宁 葫芦岛 125105
    2. 光电信息控制和安全技术重点实验室,天津 300308

Abstract: The simulation of object occlusion strategies in data augmentation sets all the pixels in the randomly cropped region of the input image to zero, which erases the effective texture features and leads to poor network generalization. Therefore, this paper proposes a novel data augmentation method known as the “ChannelCut” method. The “ChannelCut” includes two methods: ChannelCut1 and ChannelCut2. Firstly, three square regions are randomly selected on the input image, and the channels of the input image are split to three channel images. Secondly, the ChannelCut1 method selects a square region on the three channel images respectively. The pixels selected by the three channels are different from each other and are set to zero. At the same time, the ChannelCut2 method retains the pixels of the square area selected on each channel in the ChannelCut1 method, and the pixels of the other two square areas corresponding to the channel are set to zero. Finally, the two methods merge the three channel images together to obtain two random channel perturbed images. The proposed method is fused into CNN models such as Resnet18, ShuffleNet V2, MobileNet V3 and experiments are carried out on five datasets such as CIFAR-10 and Image-nette. The results show that the proposed method has a better classification accuracy than the mainstream method on five datasets. Furthermore, the baseline performance has shown a significant improvement. The proposed method has advantages in fine-grained image classification and outperforms the automatic data enhancement type method that uses reinforcement learning in terms of time performance. The ChannelCut method has strong generality and effectiveness, can retain image texture features to different degrees, and enrich image diversity, significantly improving the robustness and generalization of the convolutional neural network model.

Key words: data augmentation, occlusion simulation, channel perturbation, texture features, image classification

摘要: 数据增强中遮挡仿真方法将输入图像随机裁剪的区域像素全部置零,会擦除有效纹理特征,导致网络泛化能力欠佳。因此,提出一种随机通道扰动的图像数据增强方法(ChannelCut)。ChannelCut方法包括ChannelCut1和ChannelCut2两种方法。在输入图像上随机选取三个方形区域,并且对输入图像进行通道分离,得到三个通道图像;ChannelCut1方法在三个通道图像上分别选取一个方形区域将其像素置零,且三个通道选择的区域互不相同;ChannelCut2方法保留ChannelCut1方法中选取的方形区域像素,并将每个通道中剩余两个方形区域的像素置零;将两种方法处理后的三个通道图像分别进行合并,得到两种随机通道扰动图像。将所提方法融合到Resnet18、ShuffleNet V2、MobileNet V3等CNN模型中,并在CIFAR-10、Imagenette等五个数据集上开展实验。该方法在五个数据集上的分类准确率均优于主流方法,显著提高了基线模型的性能;在细粒度图像分类中更占有优势;在时间性能上优于使用强化学习的自动数据增强类型方法。该方法能够不同程度地保留图像纹理特征,丰富图像多样性,具有较强的通用性和有效性,显著地提高卷积神经网络模型的鲁棒性和泛化性。

关键词: 数据增强, 遮挡仿真, 通道扰动, 纹理特征, 图像分类