Multi-Scale Dense Networks for Resource Efficient Image Classification release_kgrj6pahbbahfocsfwdpdnyc54

by Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger

Released as a article .

2018  

Abstract

In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network's prediction for a test example is progressively updated, facilitating the output of a prediction at any time; and 2. budgeted batch classification, where a fixed amount of computation is available to classify a set of examples that can be spent unevenly across "easier" and "harder" inputs. In contrast to most prior work, such as the popular Viola and Jones algorithm, our approach is based on convolutional neural networks. We train multiple classifiers with varying resource demands, which we adaptively apply during test time. To maximally re-use computation between the classifiers, we incorporate them as early-exits into a single deep convolutional neural network and inter-connect them with dense connectivity. To facilitate high quality classification early on, we use a two-dimensional multi-scale network architecture that maintains coarse and fine level features all-throughout the network. Experiments on three image-classification tasks demonstrate that our framework substantially improves the existing state-of-the-art in both settings.
In text/plain format

Archived Files and Locations

application/pdf  7.8 MB
file_i737ioyymndmpkfdzggbjkmavm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-06-07
Version   v5
Language   en ?
arXiv  1703.09844v5
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: ebbd25a5-e11b-4ed8-9afa-24011e4caf65
API URL: JSON