Information Bottleneck Disentanglement for Identity Swapping
文献类型:会议论文
作者 | Gao, Gege3; Huang, Huaibo3; Fu, Chaoyou1,3; Li, Zhaoyang; He, Ran1,2,3 |
出版日期 | 2021 |
会议日期 | 2021.6.19 |
会议地点 | 线上 |
英文摘要 | Improving the performance of face forgery detectors often requires more identity-swapped images of higher-quality. One core objective of identity swapping is to generate identity-discriminative faces that are distinct from the target while identical to the source. To this end, properly disentangling identity and identity-irrelevant information is critical and remains a challenging endeavor. In this work, we propose a novel information disentangling and swapping network, called InfoSwap, to extract the most expressive information for identity representation from a pre-trained face recognition model. The key insight of our method is to formulate the learning of disentangled representations as optimizing an information bottleneck trade-off, in terms of finding an optimal compression of the pretrained latent features. Moreover, a novel identity contrastive loss is proposed for further disentanglement by requiring a proper distance between the generated identity and the target. While the most prior works have focused on using various loss functions to implicitly guide the learning of representations, we demonstrate that our model can provide explicit supervision for learning disentangled representations, achieving impressive performance in generating more identity-discriminative swapped faces. |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/48685] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | He, Ran |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Center for Excellence in Brain Science and Intelligence Technology, CAS 3.National Laboratory of Pattern Recognition, CASIA |
推荐引用方式 GB/T 7714 | Gao, Gege,Huang, Huaibo,Fu, Chaoyou,et al. Information Bottleneck Disentanglement for Identity Swapping[C]. 见:. 线上. 2021.6.19. |
入库方式: OAI收割
来源:自动化研究所
其他版本
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。