面向皮肤镜图像识别的内卷胶囊网络  

Involutional Capsule Network for Dermoscopy Image Recognition

作　　者：王凌翔 张莉[1] WANG Lingxiang;ZHANG Li(School of Computer Science and Technology,Soochow University,Suzhou 215008)

机构地区：[1]苏州大学计算机科学与技术学院,苏州215008

出　　处：《模式识别与人工智能》2024年第11期986-998,共13页Pattern Recognition and Artificial Intelligence

基　　金：江苏省六大人才高峰项目(No.XYDXX-054)资助。

摘　　要：皮肤镜图像识别能区分皮肤病变,有助于皮肤癌的早期诊断.为了提高皮肤镜图像识别效率,文中提出面向皮肤镜图像识别的内卷胶囊网络(Involutional Capsule Network,InvCNet),融合内卷操作和全局注意力机制(Global Attention Mechanism,GAM),并去除重构部分.内卷操作融合特征图在通道上的信息,提供丰富的细节,增强皮肤镜图像特征.GAM减轻卷积和池化操作引起的空间信息损失,放大跨维度交互.在4个皮肤镜图像数据集上的实验表明,InvCNet大幅减少网络参数量,并在多数数据集上性能较优.Dermoscopy image recognition can distinguish skin lesions and it is helpful for the early diagnosis of skin cancer.To enhance the efficiency of dermoscopy image recognition,an involutional capsule network(InvCNet)is proposed.InvCNet combines an involutional operation and a global attention mechanism(GAM),while the reconstruction part is removed.The involution operation provides rich minutiae to enhance the dermoscopy image features by fusing information of feature maps across channels.Meanwhile,GAM is employed to mitigate the loss of spatial information induced by the convolution and pooling operations and amplify the cross-dimensional interactions.Experiments on four public datasets demonstrate that InvCNet significantly reduces the number of network parameters while achieving superior performance on most datasets.

关 键 词：图像分类 皮肤病变 胶囊网络 全局注意力机制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]