Beyond vanilla convolution : random pixel difference convolution for face perception
|Author:||Liu, Wenzhe1; Su, Zhuo2; Liu, Li1,2|
1College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
2Center for Machine Vision and Signal Analysis, University of Oulu, 90570 Oulu, Finland
|Online Access:||PDF Full Text (PDF, 2.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2021111154658
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2021-11-11
Face perception is an essential and significant problem in pattern recognition, concretely including Face Recognition (FR), Facial Expression Recognition (FER), and Race Categorization (RC). Though handcrafted features perform well on face images, Deep Convolutional Neural Networks (DCNNs) have brought new vitality to this field recently. Vanilla DCNNs are powerful at learning high-level semantic features, but are weak in capturing low-level image characteristic changes in illumination, intensity, and texture regarded as key traits in facial processing and feature extraction, which is alternatively the strength of human-designed feature descriptors. To integrate the best of both worlds, we proposed novel Random Pixel Difference Convolution (RPDC) which is efficient alternatives to vanilla convolutional layers in standard CNNs and can promote to extract discriminative and diverse facial features. By means of searched RPDC of high efficiency, we build S-RaPiDiNet, and achieve promising and extensive experiment results in FR ( ≈0.5 % improvement), FER (over 1% growth), and RC (0.25%–3% increase) than baseline network in vanilla convolution, showing strong generalization of RPDC.
|Pages:||139248 - 139259|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
This work was supported by the National Natural Science Foundation of China under Grant 61872379.
© The Authors 2021. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.