摘要
针对多数数据增强方法在裁剪区域的选择中过于随机,以及多数方法过分关注图像中的特征显著区域而忽略了对图像中鉴别性较差区域进行加强学习,提出SaliencyOut以及SaliencyCutMix方法,旨在加强对图像中鉴别性较差区域特征的学习。具体来说,SaliencyOut首先利用显著性检测技术生成原图像的显著性映射图,之后在显著性图中寻找一个特征显著区域,接着将此区域中的像素去除。SaliencyCutMix则是将原图像的裁剪区域去除之后,使用补丁图像中相同区域的图块进行替换。通过对图像中部分特征显著区域的遮挡或替换,引导模型学习关于目标对象的其他特征。此外,针对在裁剪区域较大时,可能丢失过多显著特征区域的问题,提出在裁剪边界的选定中加入自适应缩放因子。该因子可以根据裁剪区域边界初始大小的不同,动态地调整裁剪边界。在4个数据集中的实验表明:本文方法可显著提升模型的分类性能以及抗干扰能力,优于多数先进方法。尤其是在Mini-ImageNet数据集中,应用于ResNet-34网络,SaliencyCutMix相较于CutMix的Top-1准确率提升了1.18%。
In view of the fact that most data augmentation methods tend to be overly random in their selection of cropped regions,and tend to place too much emphasis on the feature salient regions in the image while neglecting the reinforcement learning of the poorly discriminative regions in the image,the SaliencyOut and SaliencyCutMix methods were proposed to enhance the learning of poorly discriminative regions in images.Specifically,SaliencyOut first employed the saliency detection technology to generate a saliency map of the original image,subsequently identifying a feature salient area in the saliency map and removing the pixels in this area.SaliencyCutMix,on the other hand,removed the cropped area of the original image and replaced it with the same area of the patch image.By occluding or replacing some feature salient areas in the image,the model was guided to learn other features about the target object.In addition,to address the issue of losing too many salient feature regions in the cases of large cropping areas,an adaptive scaling factor was incorporated in the selection of the cropping boundary.This factor enabled the dynamic adjustment of the size of the cropping boundary according to the difference in the initial size of the cropping area boundary.Experimental results on four datasets showed that the proposed method could significantly improve the classification performance and anti-interference ability of the model,surpassing most advanced methods.In particular,in the Mini-ImageNet dataset,when applied to the ResNet-34 network,SaliencyCutMix could improve the Top-1 accuracy by 1.18%compared to CutMix.
作者
曾武
朱恒亮
邢树礼
林江宏
毛国君
ZENG Wu;ZHU Heng-iang;XING Shu-i;LIN Jiang-hong;MAO Guo-jun(School of Computer Science and Mathematics,Fujian University of Technology,Fuzhou Fujian 350118,China;Fujian Key Laboratory of Big Data Mining and Applications,Fuzhou Fujian 350118,China)
出处
《图学学报》
CSCD
北大核心
2023年第2期260-270,共11页
Journal of Graphics
基金
国家自然科学基金项目(61773415)
国家重点研发项目(2019YFD0900805)。
关键词
数据增强
图像分类
深度学习
显著性检测
图像混合
data enhancement
image classification
deep learning
saliency detection
image mixing
