摘要
卷积神经网络(convolutional neural network, CNN)被广泛用于图像分类任务中。大多数现有的CNN模型都按照N路分类器的形式训练。然而,不同类别之间总存在差异性限制了N路分类器的分类能力。为了解决上述问题,提出的神经网络模型将混淆树结构(confusion tree, CT)和CNN模型结合,设计了性能更强的基于混淆树的卷积神经网络模型(confusion tree CNN,CT-CNN)。该模型首先建立一个混淆树来对类别之间的混淆性进行建模;然后,将混淆树的分层结构嵌入到CNN模型中,通过这种方式可以引导CNN的训练过程更加关注混淆性强的类别集合。该模型在公共数据集上进行了评估,实验结果证明,CT-CNN能克服大规模数据类别间的分类难度分布不均匀的局限,在复杂大规模的分类任务中取得稳定的优秀表现。
CNN(convolutional neural network) is widely used in image classification tasks.Most existing CNN-based classification models are trained as flat N-way classifiers.However, the difference among different image categories limits the capacity of the classifier.To solve the problem, this paper proposed CT-CNN(confusion tree convolutional neural network) model which combined the CT with CNN.CT-CNN first established a CT to identify the confused categories.Then it embedded the hierarchical structure of CT into CNN model, which leaded the CNN training procedure to pay more attention on strongly confused categories.Experiments on public datasets prove that CT-CNN can overcome the limitation of uneven distribution of classification difficulty between categories of large-scale datasets and achieve better performance on complex large-scale image classification tasks.
作者
刘运韬
李渊
刘逊韵
Liu Yuntao;Li Yuan;Liu Xunyun(Dept.of Computer Science,National University of Defense Technology,Changsha 410073,China;Institute of War,Academy of Military Science,Beijing 100097,China)
出处
《计算机应用研究》
CSCD
北大核心
2022年第3期938-942,共5页
Application Research of Computers
基金
国家自然科学基金资助项目。
关键词
深度学习
社区发现
图像分类
混淆图
deep learning
community detection
image classification
confusion graph
