基于ECA-Net与多尺度结合的细粒度图像分类方法

针对细粒度图像分类问题提出了一种有效的算法以实现端到端的细粒度图像分类.ECA-Net中ECA(efficient channel attention)模块是一种性能优势显著的通道注意力机制,将其与经典网络ResNet-50进行融合构成新的基础卷积神经网络ResEca;通过物体级图像定位模块与部件级图像生成模块生成物体级图像和部件级图像,并结合原始图像作为网络的输入,构建以ResEca为基础的三支路网络模型Tb-ResEca-Net(three branch of ResEca network).该算法在公有数据集CUB-200-2011、FGVC-aircraft和Stanford cars datasets上进行测试训练,分别取得了89.9％、95.1％和95.3％的准确率.实验结果表明,该算法相较于其他传统的细粒度分类算法具有较高的分类准确率以及较强的鲁棒性,是一种有效的细粒度图像分类方法.

Fine-grained image classification method based on ECA-Net and multi-scale

Aiming at the problem of fine-grained visual categorization, this paper proposed an effective algorithm to achieve end-to-end fine-grained visual categorization. The ECA module in ECA-Net was a channel attention mechanism with significant performance advantages. It model-fused with the classic network ResNet-50 to form the ResEca. Then, it used the object-level image positioning module and the part-level image generation module to generate object-level and part-level images. Those images combined with original images could be as the input of the new constructed network Tb-ResEca-Net. This paper trained the model on the public datasets CUB-200-2011, FGVC-Aircraft and Stanford cars datasets, and the accuracy obtained 89.9%, 95.1% and 95.3% respectively on the test set of the corresponding dataset. The experimental results show that this method has higher classification accuracy and stronger robustness compares with other traditional fine-grained classification methods, which is an effective fine-grained image classification method.