Abstract
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.
Abstract (translated)
准确地对细粒度图像进行分类仍然是一个挑战，特别是在基于卷积操作或自注意力机制的骨干网络中。本研究提出了新颖的双核神经网络（DCNN），结合卷积操作和自注意力机制的优点，以提高细粒度图像分类的准确性。构建弱监督学习骨干模型的DCNN的主要新颖设计特征包括：（a）提取异质数据，（b）保持特征图分辨率不变，（c）扩大感受野，（d）融合全局表示和局部特征。实验结果表明，将DCNN作为分类某些细粒度基准数据集的骨干网络，相比于其他基于卷积或自注意力机制的细粒度骨干网络，性能优势分别达到了13.5--19.5%和2.2--12.9%。
URL
https://arxiv.org/abs/2405.04093
