Multi-target deep neural networks: Theoretical analysis and implementation

In this work, we propose a novel deep neural network referred to as Multi-Target Deep Neural Network (MT-DNN). We theoretically prove that different stable target models with shared learning paths are stable and can achieve optimal solutions respectively. Based on GoogleNet, we design a single model...

Full description

Saved in:
Bibliographic Details
Main Authors: ZENG, Zeng, LIANG, Nanying, YANG, Xulei, HOI, Steven C. H.
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2018
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4187
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5190
record_format dspace
spelling sg-smu-ink.sis_research-51902018-12-07T02:30:19Z Multi-target deep neural networks: Theoretical analysis and implementation ZENG, Zeng LIANG, Nanying YANG, Xulei HOI, Steven C. H. In this work, we propose a novel deep neural network referred to as Multi-Target Deep Neural Network (MT-DNN). We theoretically prove that different stable target models with shared learning paths are stable and can achieve optimal solutions respectively. Based on GoogleNet, we design a single model with three different targets, one for classification, one for regression, and one for masks that is composed of 256  ×  256 sub-models. Unlike bounding boxes used in ImageNet, our single model can draw the shapes of target objects, and in the meanwhile, classify the objects and calculate their sizes. We validate our single MT-DNN model via rigorous experiments and prove that the multiple targets can boost each other to achieve optimization solutions. 2018-01-17T08:00:00Z text https://ink.library.smu.edu.sg/sis_research/4187 info:doi/10.1016/j.neucom.2017.08.044 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Object detection Segmentation Learning path Multi-target deep learning Deep neural networks Databases and Information Systems OS and Networks
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Object detection
Segmentation
Learning path
Multi-target deep learning
Deep neural networks
Databases and Information Systems
OS and Networks
spellingShingle Object detection
Segmentation
Learning path
Multi-target deep learning
Deep neural networks
Databases and Information Systems
OS and Networks
ZENG, Zeng
LIANG, Nanying
YANG, Xulei
HOI, Steven C. H.
Multi-target deep neural networks: Theoretical analysis and implementation
description In this work, we propose a novel deep neural network referred to as Multi-Target Deep Neural Network (MT-DNN). We theoretically prove that different stable target models with shared learning paths are stable and can achieve optimal solutions respectively. Based on GoogleNet, we design a single model with three different targets, one for classification, one for regression, and one for masks that is composed of 256  ×  256 sub-models. Unlike bounding boxes used in ImageNet, our single model can draw the shapes of target objects, and in the meanwhile, classify the objects and calculate their sizes. We validate our single MT-DNN model via rigorous experiments and prove that the multiple targets can boost each other to achieve optimization solutions.
format text
author ZENG, Zeng
LIANG, Nanying
YANG, Xulei
HOI, Steven C. H.
author_facet ZENG, Zeng
LIANG, Nanying
YANG, Xulei
HOI, Steven C. H.
author_sort ZENG, Zeng
title Multi-target deep neural networks: Theoretical analysis and implementation
title_short Multi-target deep neural networks: Theoretical analysis and implementation
title_full Multi-target deep neural networks: Theoretical analysis and implementation
title_fullStr Multi-target deep neural networks: Theoretical analysis and implementation
title_full_unstemmed Multi-target deep neural networks: Theoretical analysis and implementation
title_sort multi-target deep neural networks: theoretical analysis and implementation
publisher Institutional Knowledge at Singapore Management University
publishDate 2018
url https://ink.library.smu.edu.sg/sis_research/4187
_version_ 1770574396551856128