arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2006.09618cs.CV
收藏

多子空间神经网络用于图像识别

Multi-Subspace Neural Network for Image Recognition

Chieh-Ning Fang, Chin-Teng Lin

摘要:

在图像分类任务中,特征提取一直是一个重要的问题。类内变异性增加了设计提取器的难度。此外,手工制作的特征提取器不能简单地适应新的情况。最近,深度学习在从数据中自动学习特征方面引起了很多关注。在这项研究中,我们提出了多子空间神经网络(MSNN),它集成了卷积神经网络(CNN)的关键组成部分,感受野,子空间的概念。将子空间与深度网络相关联是一种新颖的设计,提供了数据的各种观点。由自适应子空间自组织映射(ASSOM)训练的基向量跨越子空间,作为传递函数来访问轴向分量并定义感受野以提取数据的基本模式,而不会扭曲视觉任务中的拓扑结构。此外,多子空间策略被实现为并行块,以适应真实世界的数据,并提供各种数据解释,希望能够更强大地处理类内变异性问题。为此,手写数字和对象图像数据集(即,MNIST和COIL-20)进行分类,以验证所提出的MSNN结构。实验结果表明,MSNN是有竞争力的其他国家的最先进的方法。

英文摘要:

In image classification task, feature extraction is always a big issue. Intra-class variability increases the difficulty in designing the extractors. Furthermore, hand-crafted feature extractor cannot simply adapt new situation. Recently, deep learning has drawn lots of attention on automatically learning features from data. In this study, we proposed multi-subspace neural network (MSNN) which integrates key components of the convolutional neural network (CNN), receptive field, with subspace concept. Associating subspace with the deep network is a novel designing, providing various viewpoints of data. Basis vectors, trained by adaptive subspace self-organization map (ASSOM) span the subspace, serve as a transfer function to access axial components and define the receptive field to extract basic patterns of data without distorting the topology in the visual task. Moreover, the multiple-subspace strategy is implemented as parallel blocks to adapt real-world data and contribute various interpretations of data hoping to be more robust dealing with intra-class variability issues. To this end, handwritten digit and object image datasets (i.e., MNIST and COIL-20) for classification are employed to validate the proposed MSNN architecture. Experimental results show MSNN is competitive to other state-of-the-art approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑