基于显著增强分层双线性池化网络的细粒度图像分类

Saliency Enhanced Hierarchical Bilinear Pooling for Fine-Grained Classification

分层双线性池化网络考虑了中间卷积层的特征交互,对细粒度图像起到了良好的分类效果,但它对一幅图像包括无关背景在内的所有区域激活都进行了特征交互,会影响分类性能.针对该问题,提出一种显著增强的分层双线性池化方法.该方法在分层双线性池化网络的基础上,结合显著性检测网络生成注意力图,使用注意力图与特征提取网络进行交互实现对显著区域的信息增强,减少了背景等无关信息的影响,提高了分类性能.在3个常用的细粒度图像数据集CUB-200-2011,Stanford Cars和FGVC-Aircraft上均进行了实验,分类准确率分别为86.5%,92.9%和90.8%,与当前其他主流方法相比,取得了良好的分类效果.

Hierarchical bilinear pooling network considers the feature interaction in middle convolutional layers and works well in the classification of fine-grained images.However,it carries out feature interaction on all activated image regions including irrelevant background,which affects the classification performance.To address this problem,a saliency enhanced hierarchical bilinear pooling method is proposed,which combines with the saliency detection network to generate an attention map,and uses the attention map to interact with the feature extraction network to enhance the information of the salient regions.As the result,it can reduce the impact of background and other irrelevant information,and improve the classification performance.The classification accuracy on three commonly used fine-grained image datasets CUB-200-2011,Stanford Cars and FGVC-Aircraft is 86.5%,92.9%and 90.8%,respectively,which is excellent compared with other mainstream methods.