Zhu Lei, Lu Xu, Cheng Zhiyong, Li Jingjing, Zhang Huaxiang
IEEE Trans Image Process. 2020 Feb 21. doi: 10.1109/TIP.2020.2974065.
Hashing could significantly accelerate large-scale image search by transforming the high-dimensional features into binary Hamming space, where efficient similarity search can be achieved with very fast Hamming distance computation and extremely low storage cost. As an important branch of hashing methods, multi-view hashing takes advantages of multiple features from different views for binary hash learning. However, existing multi-view hashing methods are either based on shallow models which fail to fully capture the intrinsic correlations of heterogeneous views, or unsupervised deep models which suffer from insufficient semantics and cannot effectively exploit the complementarity of view features. In this paper, we propose a novel Deep Collaborative Multi-view Hashing (DCMVH) method to deeply fuse multi-view features and learn multi-view hash codes collaboratively under a deep architecture. DCMVH is a new deep multi-view hash learning framework. It mainly consists of 1) multiple view-specific networks to extract hidden representations of different views, and 2) a fusion network to learn multi-view fused hash code. DCMVH associates different layers with instance-wise and pair-wise semantic labels respectively. In this way, the discriminative capability of representation layers can be progressively enhanced and meanwhile the complementarity of different view features can be exploited effectively. Finally, we develop a fast discrete hash optimization method based on augmented Lagrangian multiplier to efficiently solve the binary hash codes. Experiments on public multi-view image search datasets demonstrate our approach achieves substantial performance improvement over state-of-the-art methods.
哈希技术可以通过将高维特征转换到二进制汉明空间，显著加速大规模图像搜索，在该空间中，可以通过非常快速的汉明距离计算和极低的存储成本实现高效的相似性搜索。作为哈希方法的一个重要分支，多视图哈希利用来自不同视图的多个特征进行二进制哈希学习。然而，现有的多视图哈希方法要么基于浅层模型，无法充分捕捉异构视图的内在相关性，要么基于无监督深度模型，存在语义不足的问题，无法有效利用视图特征的互补性。在本文中，我们提出了一种新颖的深度协作多视图哈希（DCMVH）方法，以在深度架构下深度融合多视图特征并协同学习多视图哈希码。DCMVH是一个新的深度多视图哈希学习框架。它主要由1）多个特定于视图的网络组成，用于提取不同视图的隐藏表示，以及2）一个融合网络，用于学习多视图融合哈希码。DCMVH分别将不同层与实例级和成对语义标签相关联。通过这种方式，可以逐步增强表示层的判别能力，同时有效利用不同视图特征的互补性。最后，我们基于增广拉格朗日乘数开发了一种快速离散哈希优化方法，以有效地求解二进制哈希码。在公共多视图图像搜索数据集上的实验表明，我们的方法比现有方法取得了显著的性能提升。
