| Adversarial Discriminative Heterogeneous Face Recognition | |
Lingxiao Song1,2; Man Zhang1,2; Xiang Wu1,2 ; Ran He1,2,3
| |
| 2018 | |
| 会议名称 | American Association for AI National Conference(AAAI) |
| 会议日期 | February 2–7, 2018 |
| 会议地点 | New Orleans, Louisiana, USA |
| 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. |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.ia.ac.cn/handle/173211/19717 |
| 专题 | 模式识别实验室 |
| 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 |
| 第一作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
| 通讯作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
| 推荐引用方式 GB/T 7714 | Lingxiao Song,Man Zhang,Xiang Wu,et al. Adversarial Discriminative Heterogeneous Face Recognition[C],2018. |
| 条目包含的文件 | 下载所有文件 | |||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| AAAI2018_AHFR_final.（565KB） | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 | ||
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。
修改评论