University of Oulu

W. Liu, Z. Su and L. Liu, "Beyond Vanilla Convolution: Random Pixel Difference Convolution for Face Perception," in IEEE Access, vol. 9, pp. 139248-139259, 2021, doi: 10.1109/ACCESS.2021.3117955

Beyond vanilla convolution : random pixel difference convolution for face perception

Saved in:
Author: Liu, Wenzhe1; Su, Zhuo2; Liu, Li1,2
Organizations: 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
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.9 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
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.

see all

Series: IEEE access
ISSN: 2169-3536
ISSN-E: 2169-3536
ISSN-L: 2169-3536
Volume: 9
Pages: 139248 - 139259
DOI: 10.1109/ACCESS.2021.3117955
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Funding: This work was supported by the National Natural Science Foundation of China under Grant 61872379.
Copyright information: © The Authors 2021. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see