.png){kind=icon}
返回
Structured deep Fisher pruning for efficient facial trait classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2018.06.008.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
High efficiency is desirable for many interactive biometrics tasks, including facial trait recognition. Although deep convolutional nets are effective for a multitude of classification tasks, their high space and time demands make them impractical for PCs and mobile devices without a powerful GPU. In this paper, we propose a structured filter-level pruning approach based on Fisher LDA [1], which boosts efficiency while maintaining accuracy for facial trait classification. It starts from the last convolutional layer where we find filter activations are less correlated. Through Fisher's LDA, we show that this decorrelation makes it safe to discard directly filters with high within-class variance and low between-class variance. The pruning goes on by tracing deconvolution based dependency over layers. Combined with light classifiers, the reduced CNNs can achieve comparable accuracies on example facial traits from the LFWA(+) and CelebA datasets, but with large reductions in model size (96%-98% for VGG-16, 81% for GoogLeNet) and computation (as high as 80% for VGG-16, 61% for GoogLeNet). (C) 2018 Elsevier B.V. All rights reserved.
Keyword:
Neural network pruning
Fisher LDA
Facial trait classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
The FERET database and evaluation procedure for face-recognition algorithms人脸识别算法的FERET数据库和评估程序
PREAI
分享收藏
Malignant inflammatory histiocytoma (inflammatory fibrous histiocytoma) report of a patient with four lesions.png)
Cancer
CancerIF0
PREAI
分享收藏
分享收藏
查看更多内容