I am a machine learning postdoc in the School of Informatics 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. For my DPhil, I worked with Andrew Zisserman on object recognition and retrieval in art.
In May I will be joining the School of Engineering at the University of Edinburgh as a Lecturer (Assistant Professor) in Computer Vision and Machine Learning.
Papers
BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
J. Turner*, E. J. Crowley*, M. O’Boyle, A. Storkey, G. Gray
ICLR, 2020
[pdf] [arXiv] [code]
Deep Kernel Transfer in Gaussian Processes for Few-shot Learning
M. Patacchiola, J. Turner, E. J. Crowley, A. Storkey
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
IISWC, 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
NeurIPS, 2018
[pdf] [arXiv] [code]
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
IISWC, 2018
[pdf] [arXiv]
The Art of Detection
E. J. Crowley, A. Zisserman
VISART Workshop, ECCV, 2016
[pdf]
Face Painting: querying art with photos
E. J. Crowley, O. M. Parkhi, A. Zisserman
BMVC, 2015
[pdf]
In Search of Art
E. J. Crowley, A. Zisserman
VISART Workshop, ECCV, 2014
[pdf]
The State of the Art: Object Retrieval in Paintings using Discriminative Regions
E. J. Crowley, A. Zisserman
BMVC, 2014
[pdf]
Of Gods and Goats: Weakly Supervised Learning of Figurative Art
E. J. Crowley, A. Zisserman
BMVC, 2013
[pdf]
* indicates equal contribution.
BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
J. Turner*, E. J. Crowley*, M. O’Boyle, A. Storkey, G. Gray
ICLR, 2020
[pdf] [arXiv] [code]
Deep Kernel Transfer in Gaussian Processes for Few-shot Learning
M. Patacchiola, J. Turner, E. J. Crowley, A. Storkey
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
IISWC, 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
NeurIPS, 2018
[pdf] [arXiv] [code]
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
IISWC, 2018
[pdf] [arXiv]
The Art of Detection
E. J. Crowley, A. Zisserman
VISART Workshop, ECCV, 2016
[pdf]
Face Painting: querying art with photos
E. J. Crowley, O. M. Parkhi, A. Zisserman
BMVC, 2015
[pdf]
In Search of Art
E. J. Crowley, A. Zisserman
VISART Workshop, ECCV, 2014
[pdf]
The State of the Art: Object Retrieval in Paintings using Discriminative Regions
E. J. Crowley, A. Zisserman
BMVC, 2014
[pdf]
Of Gods and Goats: Weakly Supervised Learning of Figurative Art
E. J. Crowley, A. Zisserman
BMVC, 2013
[pdf]