Multi-target deep neural networks: Theoretical analysis and implementation

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:
Object detection
Segmentation
Learning path
Multi-target deep learning
Deep neural networks
Databases and Information Systems
OS and Networks
Online Access:https://ink.library.smu.edu.sg/sis_research/4200
https://ink.library.smu.edu.sg/context/sis_research/article/5203/viewcontent/Multi_target_deep_neural_networks_afv.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary: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.

Similar Items