Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision

TL;DR

This paper introduces a scalable framework for embedded computer vision that uses intermediate outputs in neural networks to control computational load and improve accuracy, demonstrated on age estimation tasks.

Contribution

It presents a novel framework incorporating intermediate outputs for flexible computation and reveals their regularization effect during training.

Findings

Intermediate outputs enable dynamic tradeoff between accuracy and speed.

Regularization effect improves prediction accuracy.

Framework tested successfully on age estimation with pretrained networks.

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.