基于多分支瓶颈结构的轻量型图像分类算法研究

Research on Lightweight Image Classification Algorithm Based on Multi-Branch Bottleneck Structure

传统卷积神经网络存在着参数量大、训练耗时长、轻量级模型的识别准确度不足的问题.本文提出了一种基于ResNet网络的多分支结构轻量化网络(Residual multi-branch structured Network,RemulbNet),通过在残差结构的主干中使用多分支结构增加特征多样性,利用变体的深度可分离卷积缩减模型参数量,采用Mish激活函数增加网络的非线性表达能力,在有效减少模型体积的情况下,提升网络的分类准确率.利用图像识别数据库,对网络性能进行测试.研究表明,对于5分类花卉识别问题,RemulbNet相比ResNet网络识别准确率提高3.9%,模型参数量减小71%,模型体积减小77%,缩短了约40%训练耗时;与轻量级网络(MobileNet v2和ShuffleNet v2)相比,RemulbNet在识别准确度、模型体积、训练时长和不同的图像分类数据集上都表现出优良的性能.

The traditional convolutional neural networks have many problems,such as large number of parameters,long training time,and insufficient recognition accuracy of the lightweight models.Based on ResNet network,a lightweight network named RemulbNet(Residual multi-branch structured Network)with multi-branch structure,which increases fea-ture diversity with multi-branch structure in the backbone of the residual structure,reduces the number of model parameters with the depth-separable convolution of variants,and also increases the nonlinear expression capability of the network with Mish activation function.These measures can effectively reduce the model volume and improve the classification accuracy of the network.Using the image recognition database,the network performance is tested.For 5 categories of flower identifi-cation,RemulbNet improves the recognition accuracy by 3.9%,reduces the number of model parameters by 71%,reduces the model volume by 77%,and shortens the training time by about 40%compared with the ResNet network.Facing differ-ent image classification datasets,RemulbNet also shows excellent performance in terms of recognition accuracy,model vol-ume,training time compared with the lightweight networks(MobileNet v2 and ShuffleNet v2).