arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.03030cs.CVcs.AIcs.LGcs.MM
收藏

基于图像集的无约束人脸识别中的依赖感知注意控制

Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets

Carnegie Mellon University(卡内基梅隆大学);University of Southern California(南加州大学);Toyota Technological Institute at Chicago(芝加哥丰田技术研究院);The Hong Kong Polytechnic University(香港理工大学)

Xiaofeng Liu, B. V. K Vijaya Kumar, Chao Yang, Qingming Tang, Jane You

摘要:

本文针对基于图像集的人脸验证与识别问题进行研究。与传统的单一媒体(图像或视频)设置不同,我们遇到了一组包含无序图像和视频的异构内容。每个图像的重要性通常被认为是相等的或基于其独立的质量评估。如何在一个集合中对无序图像的关系建模仍然是一个挑战。我们解决这个问题,制定它作为一个马尔可夫决策过程(MDP)的潜在空间。具体来说,我们首先提出了一个依赖意识的注意力控制(DAC)网络,它采用演员-评论家强化学习的顺序注意力决策的每个图像嵌入,充分利用无序图像之间丰富的相关性线索。此外,我们还引入了样本有效的变体与离线策略的经验重放,以加快学习过程。姿态引导的表示方案可以进一步提高姿态变化的极端处的性能。

英文摘要:

This paper targets the problem of image set-based face verification and identification. Unlike traditional single media (an image or video) setting, we encounter a set of heterogeneous contents containing orderless images and videos. The importance of each image is usually considered either equal or based on their independent quality assessment. How to model the relationship of orderless images within a set remains a challenge. We address this problem by formulating it as a Markov Decision Process (MDP) in the latent space. Specifically, we first present a dependency-aware attention control (DAC) network, which resorts to actor-critic reinforcement learning for sequential attention decision of each image embedding to fully exploit the rich correlation cues among the unordered images. Moreover, we introduce its sample-efficient variant with off-policy experience replay to speed up the learning process. The pose-guided representation scheme can further boost the performance at the extremes of the pose variation.

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。

↑