arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.06997cs.CV
收藏

用于人脸表情识别的峰值引导深度网络

Peak-Piloted Deep Network for Facial Expression Recognition

National University of Singapore(新加坡国立大学);University of California, San Diego(加利福尼亚大学圣迭戈分校);Carnegie Mellon University(卡内基梅隆大学);AI Institute(360人工智能研究院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

Xiangyun Zhao, Xiaodan Liang, Luoqi Liu, Teng Li, Yugang Han, Nuno Vasconcelos, Shuicheng Yan

摘要:

用于训练面部相关识别任务(如面部表情识别(FER))的深度网络的目标函数通常独立考虑每个样本。在这项工作中,我们提出了一种新的峰值引导深度网络(PPDN),它使用具有峰值表达的样本(简单样本)来监督相同类型和相同主题的非峰值表达样本(硬样本)的中间特征响应。因此,从非峰值表达到峰值表达的表达进化过程可以隐式地嵌入到网络中,以实现表达强度的不变性。提出了一种特殊用途的反向传播过程,峰值梯度抑制(PGS),用于网络训练。它将非峰值表达样本的中间层特征响应驱动到对应峰值表达样本的中间层特征响应,同时避免反向。这避免了由于来自其非峰表达对应物的干扰而降低峰表达样品的识别能力。在Oulu-CASIA和CK+两个流行的FER数据集上进行了广泛的比较,证明了PPDN相对于最先进的FER方法的优越性,以及网络结构和优化策略的优势。此外,还表明PPDN是一种通用体系结构,可以通过适当定义峰值和非峰值样本来扩展到其他任务。这是验证的实验,显示国家的最先进的性能姿态不变的人脸识别,使用多PIE数据集。

英文摘要:

Objective functions for training of deep networks for face-related recognition tasks, such as facial expression recognition (FER), usually consider each sample independently. In this work, we present a novel peak-piloted deep network (PPDN) that uses a sample with peak expression (easy sample) to supervise the intermediate feature responses for a sample of non-peak expression (hard sample) of the same type and from the same subject. The expression evolving process from non-peak expression to peak expression can thus be implicitly embedded in the network to achieve the invariance to expression intensities. A special purpose back-propagation procedure, peak gradient suppression (PGS), is proposed for network training. It drives the intermediate-layer feature responses of non-peak expression samples towards those of the corresponding peak expression samples, while avoiding the inverse. This avoids degrading the recognition capability for samples of peak expression due to interference from their non-peak expression counterparts. Extensive comparisons on two popular FER datasets, Oulu-CASIA and CK+, demonstrate the superiority of the PPDN over state-ofthe-art FER methods, as well as the advantages of both the network structure and the optimization strategy. Moreover, it is shown that PPDN is a general architecture, extensible to other tasks by proper definition of peak and non-peak samples. This is validated by experiments that show state-of-the-art performance on pose-invariant face recognition, using the Multi-PIE dataset.

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。

↑