Elliot J. Crowley
pdb

I am a Lecturer (Assistant Professor) in Machine Learning and Computer Vision at the School of Engineering in the University of Edinburgh. I am a member of the Bayesian and Neural Systems research group.

My research interests include:

  • simplifying deep learning
  • neural architecture search
  • efficient training and inference
  • weakly supervised learning in vision
  • applying machine learning to engineering

Previously, I was a postdoc at the School of Informatics in Edinburgh. I have an MEng in Engineering Science and a DPhil (PhD) from the University of Oxford.

I am co-organising the Fourth Workshop on Neural Architecture Search, Third lightweight NAS challenge at CVPR 2023. Website coming soon!

Latest Work

GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

ICLR 2023 (Accepted as a notable paper)

Chenhongyi Yang*, Jiarui Xu*, Shalini De Mello, Elliot J. Crowley, Xiaolong Wang

A new vision transformer architecture that serves as an excellent backbone across different fine-grained vision tasks.

Plug and Play Active Learning for Object Detection

Preprint, November 2022

Chenhongyi Yang, Lichao Huang, Elliot J. Crowley

An active learning framework that generalises across detectors, requiring no changes to training routines or architectures.

Selected Publications

Prediction-Guided Distillation for Dense Object Detection

ECCV 2022

Chenhongyi Yang, Mateusz Ochal, Amos Storkey, Elliot J. Crowley

A knowledge distillation framework for single stage detectors that uses a few key predictive regions to obtain high performance.

Neural Architecture Search without Training

ICML 2021 (Long talk)

Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley

A low-cost measure for scoring networks at initialisation that can be used to perform neural architecture search in seconds.

Neural Architecture Search as Program Transformation Exploration

ASPLOS 2021 (Distinguished Paper)

Jack Turner, Elliot J. Crowley, Michael O'Boyle

A compiler-oriented approach to neural architecture search which can generate new convolution operations.

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

NeurIPS 2020 (Spotlight)

Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Michael O'Boyle, Amos Storkey

A simple Bayesian alternative to standard meta-learning.

BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget

ICLR 2020

Jack Turner*, Elliot J. Crowley*, Michael O'Boyle, Amos Storkey, Gavia Gray

A fast algorithm for obtaining a compressed network architecture using Fisher information.

* equal contribution. A full list of publication is on Scholar.

Thanks to Jack Turner and Chenhongyi Yang for the website template.