论文标题
用于深度表示学习和图像群集的光谱分析网络
Spectral Analysis Network for Deep Representation Learning and Image Clustering
论文作者
论文摘要
深度表示学习是多媒体分析中的至关重要程序,并引起了越来越多的关注。大多数流行技术都依赖卷积神经网络,并且需要大量的训练程序标记数据。但是,由于成本限制,在某些任务中获取标签信息是耗时的,甚至不可能。因此,有必要开发无监督的深度表示学习技术。本文提出了一种基于光谱分析的无监督深度表示学习的新网络结构,这是一种具有坚实理论基础的流行技术。与现有的光谱分析方法相比,所提出的网络结构至少具有三个优点。首先,它可以在斑块级别中识别图像之间的局部相似性,从而在遮挡方面更健壮。其次,通过多个连续的光谱分析程序,提出的网络可以学习更多群集友好的表示,并能够揭示数据样本之间的深度相关性。第三,它可以优雅地整合不同的光谱分析程序,以便每个光谱分析程序可以在处理不同的数据样本分布时具有个人优势。广泛的实验结果表明,所提出的方法对各种图像聚类任务的有效性。
Deep representation learning is a crucial procedure in multimedia analysis and attracts increasing attention. Most of the popular techniques rely on convolutional neural network and require a large amount of labeled data in the training procedure. However, it is time consuming or even impossible to obtain the label information in some tasks due to cost limitation. Thus, it is necessary to develop unsupervised deep representation learning techniques. This paper proposes a new network structure for unsupervised deep representation learning based on spectral analysis, which is a popular technique with solid theory foundations. Compared with the existing spectral analysis methods, the proposed network structure has at least three advantages. Firstly, it can identify the local similarities among images in patch level and thus more robust against occlusion. Secondly, through multiple consecutive spectral analysis procedures, the proposed network can learn more clustering-friendly representations and is capable to reveal the deep correlations among data samples. Thirdly, it can elegantly integrate different spectral analysis procedures, so that each spectral analysis procedure can have their individual strengths in dealing with different data sample distributions. Extensive experimental results show the effectiveness of the proposed methods on various image clustering tasks.