Accurate classification of fine-grained images remains a challenge in
backbones based on convolutional operations or self-attention mechanisms. This
study proposes novel dual-current neural networks (DCNN), which combine the
advantages of convolutional operations and self-attention mechanisms to improve
the accuracy of fine-grained image classification. The main novel design
features for constructing a weakly supervised learning backbone model DCNN
include (a) extracting heterogeneous data, (b) keeping the feature map
resolution unchanged, (c) expanding the receptive field, and (d) fusing global
representations and local features. Experimental results demonstrated that
using DCNN as the backbone network for classifying certain fine-grained
benchmark datasets achieved performance advantage improvements of 13.5--19.5%
and 2.2--12.9%, respectively, compared to other advanced convolution or
attention-based fine-grained backbones.

通过结合卷积操作和自注意机制的优势构建了新型双通道神经网络模型（DCNN），用于改进细粒度图像分类的准确性。实验证明，将 DCNN 作为骨干网络用于分类特定的细粒度基准数据集，在性能上相较于其他先进的卷积或注意力细粒度骨干网络，分别获得了 13.5％-19.5％和 2.2％-12.9％的性能优势改进。