Adversarial Discriminative Heterogeneous Face Recognition
Lingxiao Song1,2; Man Zhang1,2; Xiang Wu1,2; Ran He1,2,3
2018
会议日期February 2–7, 2018
会议地点New Orleans, Louisiana, USA
英文摘要The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via adversarial learning on both raw-pixel space and compact feature space. This framework integrates cross-spectral face hallucination and discriminative feature learning into an end-to-end adversarial network. In the pixel space, we make use of generative adversarial networks to perform cross-spectral face hallucination. An elaborate two-path model is introduced to alleviate the lack of paired images, which gives consideration to both global structures and local textures. In the feature space, an adversarial loss and a high-order variance discrepancy loss are employed to measure the global and local discrepancy between two heterogeneous distributions respectively. These two losses enhance domain-invariant feature learning and modality independent noise removing. Experimental results on three NIR-VIS databases show that our proposed approach outperforms state-of-the-art HFR methods, without requiring of complex network or large-scale training dataset.
内容类型会议论文
源URL[http://ir.ia.ac.cn/handle/173211/19717]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Ran He
作者单位1.National Laboratory of Pattern Recognition, CASIA
2.Center for Research on Intelligent Perception and Computing, CASIA
3.Center for Excellence in Brain Science and Intelligence Technology, CAS
推荐引用方式
GB/T 7714
Lingxiao Song,Man Zhang,Xiang Wu,et al. Adversarial Discriminative Heterogeneous Face Recognition[C]. 见:. New Orleans, Louisiana, USA. February 2–7, 2018.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace