arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07810cs.CVcs.LGeess.IV
收藏

区分性视觉识别的解纠缠

Disentanglement for Discriminative Visual Recognition

Harvard University(哈佛大学);Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心);Harvard Medical School(哈佛医学院)

Xiaofeng Liu

摘要:

最近基于深度学习的识别的成功依赖于维护与主任务标签相关的内容。然而,如何明确地消除噪声信号,以更好地推广在可控的方式仍然是一个悬而未决的问题。例如,诸如身份特定属性、姿态、光照和表情的各种因素影响面部图像的外观。解开身份特异性因素对面部表情识别(FER)有潜在的好处。本章系统地总结了任务相关/非相关语义变异和非特定潜在变异这两个影响翻译质量的因素。在本章中,这些问题被转换为深度度量学习问题或潜在空间中的对抗性极大极小博弈。对于前一种选择,一个广义的自适应(N+M)-元组集群损失函数与身份感知的硬否定挖掘和在线积极挖掘方案可以用于身份不变的FER。通过联合优化,在统一的两个全连接层分支框架中结合深度度量损耗和softmax损耗,可以获得更好的FER性能。对于后一种解决方案,可以为端到端条件对抗网络配备将输入样本分解为三个互补部分的能力。区分性表征继承了由任务的先验知识引导的期望的不变性属性,该属性与任务相关/不相关的语义和潜在变化无关。该框架在光照、化妆、伪装容忍人脸识别和人脸属性识别等一系列任务上都取得了很好的性能。本章系统地总结了目前流行的实用解纠缠方法,以实现更具区分力的视觉识别。

英文摘要:

Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization in a controllable manner remains an open issue. For instance, various factors such as identity-specific attributes, pose, illumination and expression affect the appearance of face images. Disentangling the identity-specific factors is potentially beneficial for facial expression recognition (FER). This chapter systematically summarize the detrimental factors as task-relevant/irrelevant semantic variations and unspecified latent variation. In this chapter, these problems are casted as either a deep metric learning problem or an adversarial minimax game in the latent space. For the former choice, a generalized adaptive (N+M)-tuplet clusters loss function together with the identity-aware hard-negative mining and online positive mining scheme can be used for identity-invariant FER. The better FER performance can be achieved by combining the deep metric loss and softmax loss in a unified two fully connected layer branches framework via joint optimization. For the latter solution, it is possible to equipping an end-to-end conditional adversarial network with the ability to decompose an input sample into three complementary parts. The discriminative representation inherits the desired invariance property guided by prior knowledge of the task, which is marginal independent to the task-relevant/irrelevant semantic and latent variations. The framework achieves top performance on a serial of tasks, including lighting, makeup, disguise-tolerant face recognition and facial attributes recognition. This chapter systematically summarize the popular and practical solution for disentanglement to achieve more discriminative visual recognition.

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。

↑