RACKNet: Robust allocation of convolutional kernels in neural networks for image classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Despite their impressive success when these hyper-parameters are suitably fine-tuned, the design of good network architectures remains an art-form rather than a science: while various search techniques, such as grid-search, have been proposed to find effective hyper-parameter configurations, often these parameters are hand-crafted (or the bounds of the search space are provided by a user). In this paper, we argue, and experimentally show, that we can minimize the need for hand-crafting, by relying on the dataset itself. In particular, we show that the dimensions, distributions, and complexities of localized features extracted from the data can inform the structure of the neural networks and help better allocate limited resources (such as kernels) to the various layers of the network. To achieve this, we first present several hypotheses that link the properties of the localized image features to the CNN and RCNN architectures and then, relying on these hypotheses, present a RACKNet framework which aims to learn multiple hyperparameters by extracting information encoded in the input datasets. Experimental evaluations of RACKNet against major benchmark datasets, such as MNIST, SVHN, CIFAR10, COIL20 and ImageNet, show that RACKNet provides significant improvements in the network design and robustness to change in the network.

Original languageEnglish (US)
Title of host publicationICMR 2019 - Proceedings of the 2019 ACM International Conference on Multimedia Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages315-323
Number of pages9
ISBN (Electronic)9781450367653
DOIs
StatePublished - Jun 5 2019
Event2019 ACM International Conference on Multimedia Retrieval, ICMR 2019 - Ottawa, Canada
Duration: Jun 10 2019Jun 13 2019

Publication series

NameICMR 2019 - Proceedings of the 2019 ACM International Conference on Multimedia Retrieval

Conference

Conference2019 ACM International Conference on Multimedia Retrieval, ICMR 2019
Country/TerritoryCanada
CityOttawa
Period6/10/196/13/19

Keywords

  • Convolutional neural networks
  • Deep learning
  • Hyper-parameter optimization
  • Meta-learning
  • Recurrent neural networks

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'RACKNet: Robust allocation of convolutional kernels in neural networks for image classification'. Together they form a unique fingerprint.

Cite this