Tampere University of Technology

TUTCRIS Research Portal

Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2018 26th European Signal Processing Conference (EUSIPCO)
PublisherIEEE
ISBN (Electronic)978-9-0827-9701-5
ISBN (Print)978-1-5386-3736-4
DOIs
Publication statusPublished - Sep 2018
Publication typeA4 Article in a conference publication
EventEuropean Signal Processing Conference -
Duration: 1 Jan 1900 → …

Publication series

Name
ISSN (Electronic)2076-1465

Conference

ConferenceEuropean Signal Processing Conference
Period1/01/00 → …

Abstract

We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables flexible control of the computational load and balances the tradeoff between accuracy and execution time. Moreover, we present an interesting finding that the intermediate outputs can act as a regularizer at training time, improving the prediction accuracy. In the experimental section we demonstrate the performance of our proposed framework with various commonly used pretrained deep networks in the use case of apparent age estimation.

Publication forum classification

Field of science, Statistics Finland