Elliot J. Crowley

elliot.j.crowley@ed.ac.uk

My photo I am a machine learning postdoc at the University of Edinburgh working with Amos Storkey in the BayesWatch group. I work on deep neural networks, and how to make them more efficient.

Prior to this, I did my MEng and DPhil at the University of Oxford.


Publications

Deep Kernel Transfer in Gaussian Processes for Few-shot Learning
M. Patacchiola, J. Turner, E. J. Crowley, A. Storkey
Preprint, 2019
[pdf] [arXiv] [code]

BlockSwap: Fisher-guided Block Substitution for Network Compression
J. Turner*, E. J. Crowley*, G. Gray, A. Storkey, M. O’Boyle
Preprint, 2019
[pdf] [arXiv] [code]

Separable Layers Enable Structured Efficient Linear Substitutions
G. Gray, E. J. Crowley, A. Storkey
Preprint, 2019
[pdf] [arXiv] [code]

Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs
V. Radu, K. Kaszyk, Y. Wen, J. Turner, J. Cano, E. J. Crowley, B. Franke, A. Storkey, M. O’Boyle
International Symposium on Workload Characterization, 2019
[pdf]

Distilling with Performance Enhanced Students
J. Turner*, E. J. Crowley*, V. Radu, J. Cano, A. Storkey, M. O’Boyle
ARM Research Summit, 2019
[pdf] [arXiv]

A Closer Look at Structured Pruning for Neural Network Compression
E. J. Crowley*, J. Turner*, A. Storkey, M. O’Boyle
CDNNRIA Workshop, NeurIPS, 2018
[pdf] [arXiv] [code]

Moonshine: Distilling with Cheap Convolutions
E. J. Crowley, G. Gray, A. Storkey
Advances in Neural Information Processing Systems (NeurIPS), 2018
[pdf] [arXiv] [code]

Dilated DenseNets for Relational Reasoning
A. Antoniou, A. Slowik, E. J. Crowley, A. Storkey
Extended Abstract, 2018
[pdf] [arXiv]

CINIC-10 is not ImageNet or CIFAR-10
L. N. Darlow, E. J. Crowley, A. Antoniou, A. Storkey
Technical Report, 2018
[pdf] [arXiv] [code]

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
J. Turner, J. Cano, V. Radu, E. J. Crowley, M. O’Boyle, A. Storkey
International Symposium on Workload Characterization, 2018
[pdf] [arXiv]

The Art of Detection
E. J. Crowley, A. Zisserman
Workshop on Computer Vision for Art Analysis, ECCV, 2016
[pdf]

Face Painting: querying art with photos
E. J. Crowley, O. M. Parkhi, A. Zisserman
British Machine Vision Conference, 2015
[pdf]

In Search of Art
E. J. Crowley, A. Zisserman
Workshop on Computer Vision for Art Analysis, ECCV, 2014
[pdf]

The State of the Art: Object Retrieval in Paintings using Discriminative Regions
E. J. Crowley, A. Zisserman
British Machine Vision Conference, 2014
[pdf]

Of Gods and Goats: Weakly Supervised Learning of Figurative Art
E. J. Crowley, A. Zisserman
British Machine Vision Conference, 2013
[pdf]

* indicates equal contribution.