Multi-target deep neural networks: Theoretical analysis and implementation

Publication Type

Journal Article

Publication Date

1-2018

Abstract

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.

Keywords

Object detection, Segmentation, Learning path, Multi-target deep learning, Deep neural networks

Discipline

Databases and Information Systems | OS and Networks

Research Areas

Data Science and Engineering

Publication

Neurocomputing

Volume

273

First Page

634

Last Page

642

ISSN

0925-2312

Identifier

10.1016/j.neucom.2017.08.044

Publisher

Elsevier

Additional URL

https://doi/10.1016/j.neucom.2017.08.044

This document is currently not available here.

Share

COinS