Searching Central Difference Convolutional Networks for Face Anti-Spoofing

By Zitong Yu, Chenxu Zhao, Zezheng Wang, Yunxiao Qin, Zhuo Su, Xiaobai Li, Feng Zhou, Guoying Zhao. 2020

569 citations recorded by the source corpus.

Face anti-spoofing (FAS) plays a vital role in face recognition systems. Most state-of-the-art FAS methods 1) rely on stacked convolutions and expert-designed network, which is weak in describing detailed fine-grained information and easily being ineffective when the environment varies (e.g., different illumination), and 2) prefer to use long sequence as input to extract dynamic features, making them difficult to deploy into scenarios which need quick response. Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information. A network built with CDC, called the Central Difference Convolutional Network (CDCN), is able to provide more robust modeling capacity than its counterpart built with vanilla convolution. Furthermore, over a specifically designed CDC search space, Neural Architecture Search (NAS) is utilized to discover a more powerful network structure (CDCN++), which can be assembled with Multiscale Attention Fusion Module (MAFM) for further boosting performance. Comprehensive experiments are performed on six benchmark datasets to show that 1) the proposed method not only achieves superior performance on intra-dataset testing (especially 0.2% ACER in Protocol-1 of OULU-NPU dataset), 2) it also generalizes well on cross-dataset testing (particularly 6.5% HTER from CASIA-MFSD to Replay-Attack datasets). The codes are available at https://github.com/ZitongYu/CDCN.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Qi Tian
2. Xiaogang Wang
3. Yi Yang
4. S. Li
5. Dacheng Tao
6. Luc Van Gool
7. Liang Zheng
8. Zhen Lei

In Information Systems

1. Guoying Zhao
2. Mohammad Rostami
3. Zhen Lei
4. Xiaobai Li
5. Zitong Yu
6. S. Li
7. Xiaoming Liu
8. Yaojie Liu

In Signal Processing

1. Zhen Lei
2. S. Li
3. Guoying Zhao
4. Zitong Yu
5. Matti Pietikäinen
6. Xiaobai Li
7. Li Liu
8. Xiangyu Zhu

Citations in the corpus

• Detection and Continual Learning of Novel Face Presentation Attacks (2021, background): “Similar to most sub-fields in computer vision, advances in deep learning, which is inspired by the nervous system [17], have led to significant face PAD improvements on benchmark datasets using convolutional neural network-based (CNN) end-to-end representation learning and classification [1, 7, 12, ”
• Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (2023, methodology): “The proposed method may be used to produce fake videos of individuals, which can be detected using some face anti-spoofing techniques[5, 51, 58].”
• Towards Fast, Accurate and Stable 3D Dense Face Alignment (2020, background): “, recognition [45,7,26,24,13,51], animation [10], avatar retargeting [9], tracking [50], attribute classification [4,22,21], image restoration [52,12,11], anti-spoofing [49,55,40,54,25].”
• Face Anti-Spoofing with Human Material Perception (2020, background): “In contrast, auxiliary depth [10,16,14] and reflection [28] supervisions are introduced to learn detailed cues effectively.”
• DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention (2023, methodology): “Given a hazy input image I ∈ R 3 × H × W , the goal of DEA-Net is to restore the corresponding haze-free image J ∈ R 3 × H × W .”
• Pixel Difference Networks for Efficient Edge Detection (2021, background): “CDC can be seen as one instantiated case of the proposed PDC (i.e., Central PDC), where the central direction is considered, as we will introduce in Section 3.”