Deep High-Order Supervised Hashing For Image Retrieval
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2018)
摘要
Recently, deep hashing has achieved excellent performances in large-scale image retrieval by simultaneously learning deep features and hashing function. However, state-of-the-art works have so far failed to explore the feature statistics higher than first-order. In this paper, to take a step towards addressing this problem, we propose two novel Deep High-order Supervised Hashing architectures (DHoSH), i.e., point-wise labels based DHoSH (DHoSH-PO) and pair-wise labels based DHoSH (DHoSH-PA). The core of DHoSH is that a trainable layer of bilinear pooling incorporates into deep convolutional neural networks (CNNs) for end-to-end learning. This layer captures the local feature interactions of the image by outer product, employing the autocorrelation information and cross-correlation information of deep features. Furthermore, our DHoSH method systematically exploits the high-order statistics of features of multiple layers. Extensive experiments on commonly used benchmarks illuminate that both DHoSH-PO and DHoSH-PA can obtain competitive improvements over its first-order counterparts, and achieve state-of-the-art performance for image retrieval task.
更多查看译文
关键词
pair-wise labels,DHoSH-PA,deep convolutional neural networks,end-to-end learning,DHoSH-PO,deep hashing,large-scale image retrieval,hashing function,feature statistics,point-wise labels,deep high-order supervised hashing architectures
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络