多尺度特征融合的细粒度图像分类

Fine-Grained Image Classification Based on Multi-Scale Feature Fusion

提出了一种基于多尺度特征融合的细粒度图像分类方法.通过运用特征金字塔结构对不同层次的特征进行尺度变换,再进行信息融合;之后筛选其中包含细节特征最多的前三个区域图,将其与图像的全局特征共同作用以判断图片所属的子类类别.在公开的细粒度数据集CUB-200-2011、Stanford Dogs上进行了实验,得到的分类精度分别为85.7%和83.5%.实验结果表明该方法对于精细化物体分类具有一定的优越性.

A fine-grained image classification method based on multiscale feature fusion is proposed.By using feature pyramid structure,the scales of different levels of features are transformed,and the information fusion is then carried out.After that,the first three regions with the most detailed features are screened out,combining with the global feature of the image to determine the subclass category of the image.The experiments are conducted on the open fine-grained data sets CUB-200-2011 and Stanford Dogs,and the classification accuracy is 85.7%and 83.5%,respectively.Experimental results show that the method has certain advantages for fine object classification.