arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.09481cs.CV
收藏

深度虹膜网络的约束设计

Constrained Design of Deep Iris Networks

Queensland University of Technology(昆士兰科技大学)

Kien Nguyen, Clinton Fookes, Sridha Sridharan

AI总结:

针对现有深度虹膜网络难以兼顾经典IrisCode的模型紧凑性与低计算量特性的问题,本文将虹膜网络设计重构为约束优化问题,实现自动化搜索最优网络,验证了经典与现有网络的最优性,并得到低算力内存需求的SOTA虹膜网络。

摘要:

尽管近期深度神经网络在虹膜识别场景中展现出良好前景,但经典IrisCode(虹膜编码)的两项关键特性——模型紧凑性与少量计算操作(FLOPs,浮点运算次数)——几乎无法通过当前的深度虹膜网络实现。本文将虹膜网络设计过程重构为一个约束优化问题,将模型规模与计算量作为学习准则纳入考量。一方面,这使得我们能够实现网络设计流程的完全自动化,以搜索受计算量与模型紧凑性约束的最优虹膜网络;另一方面,这也让我们得以探究经典IrisCode及近期虹膜网络的最优性。我们还借此学习到一个最优虹膜网络,在更少的计算与内存需求下实现了当前最优(SOTA)性能。

英文摘要:

Despite the promise of recent deep neural networks in the iris recognition setting, there are vital properties of the classic IrisCode which are almost unable to be achieved with current deep iris networks: the compactness of model and the small number of computing operations (FLOPs). This paper re-models the iris network design process as a constrained optimization problem which takes model size and computation into account as learning criteria. On one hand, this allows us to fully automate the network design process to search for the best iris network confined to the computation and model compactness constraints. On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent iris networks. It also allows us to learn an optimal iris network and demonstrate state-of-the-art performance with less computation and memory requirements.

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。

↑