NDLI: Acceleration of multi-task cascaded convolutional networks

Content Provider	IET Digital Library
Author	Ma, Long Hua Fan, Hang Yu Lu, Zhe Ming Tian, Dong
Abstract	Multi-task cascaded convolutional neural network (MTCNN) is a human face detection architecture which uses a cascaded structure with three stages (P-Net, R-Net and O-Net). The authors intend to reduce the computation time of the whole process of the MTCNN. They find that the non-maximum suppression (NMS) processes after the P-Net occupy over half of the computation time. Therefore, the authors propose a self-fine-tuning method which makes the control of computation time for the NMS process easier. Self-fine-tuning is a training trick which uses hard samples generated by P-Net to retrain P-Net. After self-fine-tuning, the distribution of human face probabilities generated by P-Net is changed, and the tail of distribution becomes thinner. The control of the number of NMS input boxes can be made easier when the distribution has a thinner tail, and choosing a suitable threshold to filter the face boxes will generate less boxes. So the computation time can be reduced. In order to keep the performance of MTCNN, the authors still propose a landmark data set augmentation, which can enhance the performance of the self-fine-tuned MTCNN. From the experiments, it is found that the proposed scheme can significantly reduce the computation time of MTCNN.
Starting Page	2435
Ending Page	2441
Page Count	7
ISSN	17519659
Volume Number	14
e-ISSN	17519667
Issue Number	Issue 11, Sep (2020)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-ipr/14/11
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2019.0141
Journal	IET Image Processing
Publisher Date	2020-04-20
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Cascaded Structure Channel Pruning Computation Time Computer Vision And Image Processing Technique Convolutional Neural Nets Convolutional Neural Network Face Boxes Face Recognition Human Face Detection Architecture Human Face Probabilities Image Recognition Knowledge Engineering Technique Learning in AI Multitask Cascaded Convolutional Network Neural Computing Technique NMS Input Boxes NMS Process Object Detection P-Net Probability Self-fine-tuned MTCNN Self-fine-tuning Method Weight Pruning
Content Type	Text
Resource Type	Article
Subject	Signal Processing Electrical and Electronic Engineering Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Thinning of convolutional neural network with mixed pruning

Palmprint gender classification by convolutional neural network

Facial expression recognition using feature additive pooling and progressive fine-tuning of CNN

Hierarchical CNN-based real-time fatigue detection system by visual-based technologies using MSP model

Face detection with a Viola–Jones based hybrid network

Crowd counting using a self-attention multi-scale cascaded network

Deep convolutional neural networks for face and iris presentation attack detection: survey and case study

FER-Net: facial expression recognition using densely connected convolutional network

Face Alignment by Coarse-to-Fine Shape Estimation

Acceleration of multi-task cascaded convolutional networks

Similar Documents

Thinning of convolutional neural network with mixed pruning

Palmprint gender classification by convolutional neural network

Facial expression recognition using feature additive pooling and progressive fine-tuning of CNN

Hierarchical CNN-based real-time fatigue detection system by visual-based technologies using MSP model

Face detection with a Viola–Jones based hybrid network

Crowd counting using a self-attention multi-scale cascaded network

Deep convolutional neural networks for face and iris presentation attack detection: survey and case study

FER-Net: facial expression recognition using densely connected convolutional network

Face Alignment by Coarse-to-Fine Shape Estimation

Acceleration of multi-task cascaded convolutional networks