论文标题

不对称转移散发与自适应二分图学习

Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning

论文作者

Lu, Jianglin, Zhou, Jie, Chen, Yudong, Pedrycz, Witold, Hung, Kwok-Wai

论文摘要

由于有效的检索速度和较低的存储消耗,学习哈希已被广泛用于视觉检索任务。但是,现有的哈希方法假定查询和检索样品位于同一域内的均匀特征空间。结果,它们不能直接应用于异质的跨域检索。在本文中,我们提出了一个广义图像转移检索(GITR)问题,该问题遇到了两个关键的瓶颈:1)查询和检索样品可能来自不同的域,导致不可避免的{域分布隙}; 2)两个域的特征可能是异质的或未对准的,从而增加了一个{功能差距}。为了解决GITR问题,我们提出了一个不对称的转移哈希(ATH)框架,其无监督/半监督/监督实现。具体而言,ATH通过两个不对称哈希函数之间的差异来表征域分布差距,并借助于跨域数据构建的新型自适应双分部分图,从而最小化特征差距。通过共同优化不对称的哈希函数和两部分图,不仅可以实现知识传递,而且还可以避免由特征比对引起的信息损失。同时,为了减轻负转移,通过涉及域亲和图来保留单域数据的固有几何结构。对不同GITR子任务下单域和跨域基准测试的广泛实验表明,与最先进的哈希方法相比,我们的ATH方法的优越性。

Thanks to the efficient retrieval speed and low storage consumption, learning to hash has been widely used in visual retrieval tasks. However, existing hashing methods assume that the query and retrieval samples lie in homogeneous feature space within the same domain. As a result, they cannot be directly applied to heterogeneous cross-domain retrieval. In this paper, we propose a Generalized Image Transfer Retrieval (GITR) problem, which encounters two crucial bottlenecks: 1) the query and retrieval samples may come from different domains, leading to an inevitable {domain distribution gap}; 2) the features of the two domains may be heterogeneous or misaligned, bringing up an additional {feature gap}. To address the GITR problem, we propose an Asymmetric Transfer Hashing (ATH) framework with its unsupervised/semi-supervised/supervised realizations. Specifically, ATH characterizes the domain distribution gap by the discrepancy between two asymmetric hash functions, and minimizes the feature gap with the help of a novel adaptive bipartite graph constructed on cross-domain data. By jointly optimizing asymmetric hash functions and the bipartite graph, not only can knowledge transfer be achieved but information loss caused by feature alignment can also be avoided. Meanwhile, to alleviate negative transfer, the intrinsic geometrical structure of single-domain data is preserved by involving a domain affinity graph. Extensive experiments on both single-domain and cross-domain benchmarks under different GITR subtasks indicate the superiority of our ATH method in comparison with the state-of-the-art hashing methods.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源