Refining Architectures of Deep Convolutional Neural Networks
View / Open Files
Authors
Shankar, S
Robertson, D
Ioannou, Y
Criminisi, A
Cipolla, R
Publication Date
2016-12-12Journal Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Conference Name
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN
1063-6919
ISBN
9781467388504
Publisher
IEEE
Volume
2016-December
Pages
2212-2220
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Shankar, S., Robertson, D., Ioannou, Y., Criminisi, A., & Cipolla, R. (2016). Refining Architectures of Deep Convolutional Neural Networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December 2212-2220. https://doi.org/10.1109/CVPR.2016.243
Abstract
© 2016 IEEE. Deep Convolutional Neural Networks (CNNs) have recently evinced immense success for various image recognition tasks [11, 27]. However, a question of paramount importance is somewhat unanswered in deep learning research - is the selected CNN optimal for the dataset in terms of accuracy and model size? In this paper, we intend to answer this question and introduce a novel strategy that alters the architecture of a given CNN for a specified dataset, to potentially enhance the original accuracy while possibly reducing the model size. We use two operations for architecture refinement, viz. stretching and symmetrical splitting. Stretching increases the number of hidden units (nodes) in a given CNN layer, while a symmetrical split of say K between two layers separates the input and output channels into K equal groups, and connects only the corresponding input-output channel groups. Our procedure starts with a pre-trained CNN for a given dataset, and optimally decides the stretch and split factors across the network to refine the architecture. We empirically demonstrate the necessity of the two operations. We evaluate our approach on two natural scenes attributes datasets, SUN Attributes [16] and CAMIT-NSAD [20], with architectures of GoogleNet and VGG-11, that are quite contrasting in their construction. We justify our choice of datasets, and show that they are interestingly distinct from each other, and together pose a challenge to our architectural refinement algorithm. Our results substantiate the usefulness of the proposed method.
Identifiers
External DOI: https://doi.org/10.1109/CVPR.2016.243
This record's URL: https://www.repository.cam.ac.uk/handle/1810/274299
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.
Recommended or similar items
The current recommendation prototype on the Apollo Repository will be turned off on 03 February 2023. Although the pilot has been fruitful for both parties, the service provider IKVA is focusing on horizon scanning products and so the recommender service can no longer be supported. We recognise the importance of recommender services in supporting research discovery and are evaluating offerings from other service providers. If you would like to offer feedback on this decision please contact us on: support@repository.cam.ac.uk