Imperial College London
Portrait Picture

Dr Ben Glocker

Faculty of Engineering, Department of Computing

Professor in Machine Learning for Imaging
 
 
 
//

Contact

 

+44 (0)20 7594 8334b.glocker Website CV

 
 
//

Location

 

377Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Pawlowski:2019,
author = {Pawlowski, N and Bhooshan, S and Ballas, N and Ciompi, F and Glocker, B and Drozdzal, M},
publisher = {arXiv},
title = {Needles in haystacks: On classifying tiny objects in large images},
url = {http://arxiv.org/abs/1908.06037v1},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - In some computer vision domains, such as medical or hyperspectral imaging, wecare about the classification of tiny objects in large images. However, mostConvolutional Neural Networks (CNNs) for image classification were developedand analyzed using biased datasets that contain large objects, most often, incentral image positions. To assess whether classical CNN architectures workwell for tiny object classification we build a comprehensive testbed containingtwo datasets: one derived from MNIST digits and other from histopathologyimages. This testbed allows us to perform controlled experiments to stress-testCNN architectures using a broad spectrum of signal-to-noise ratios. Ourobservations suggest that: (1) There exists a limit to signal-to-noise belowwhich CNNs fail to generalize and that this limit is affected by dataset size -more data leading to better performances; however, the amount of training datarequired for the model to generalize scales rapidly with the inverse of theobject-to-image ratio (2) in general, higher capacity models exhibit bettergeneralization; (3) when knowing the approximate object sizes, adaptingreceptive field is beneficial; and (4) for very small signal-to-noise ratio thechoice of global pooling operation affects optimization, whereas for relativelylarge signal-to-noise values, all tested global pooling operations exhibitsimilar performance.
AU  - Pawlowski,N
AU  - Bhooshan,S
AU  - Ballas,N
AU  - Ciompi,F
AU  - Glocker,B
AU  - Drozdzal,M
PB  - arXiv
PY  - 2019///
TI  - Needles in haystacks: On classifying tiny objects in large images
UR  - http://arxiv.org/abs/1908.06037v1
UR  - http://hdl.handle.net/10044/1/73514
ER  -
Download