Reference : Ordinal Pooling
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Electrical & electronics engineering
http://hdl.handle.net/2268/238475
Ordinal Pooling
English
Deliège, Adrien mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Istasse, Maxime [> >]
Kumar, Ashwani [> >]
De Vleeschouwer, Christophe [> >]
Van Droogenbroeck, Marc mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
2020
30th British Machine Vision Conference
Yes
No
International
British Machine Vision Conference (BMVC)
from 09-09-2019 to 12-09-2019
British Machine Vision Association
Cardiff
Wales
[en] pooling ; convolutional neural network ; deep learning ; machine learning ; ordinal pooling ; downsampling
[en] In the framework of convolutional neural networks, downsampling is often performed with an average-pooling, where all the activations are treated equally, or with a max-pooling operation that only retains an element with maximum activation while discarding the others. Both of these operations are restrictive and have previously been shown to be sub-optimal. To address this issue, a novel pooling scheme, named ordinal pooling, is introduced in this work. Ordinal pooling rearranges all the elements of a pooling region in a sequence and assigns a different weight to each element based upon its order in the sequence. These weights are used to compute the pooling operation as a weighted sum of the rearranged elements of the pooling region. They are learned via a standard gradient-based training, allowing to learn a behavior anywhere in the spectrum of average-pooling to max-pooling in a differentiable manner. Our experiments suggest that it is advantageous for the networks to perform different types of pooling operations within a pooling layer and that a hybrid behavior between average- and max-pooling is often beneficial. More importantly, they also demonstrate that ordinal pooling leads to consistent improvements in the accuracy over average- or max-pooling operations while speeding up the training and alleviating the issue of the choice of the
pooling operations and activation functions to be used in the networks. In particular, ordinal pooling mainly helps on lightweight or quantized deep learning architectures, as typically considered e.g. for embedded applications.
Montefiore Institute of Electrical Engineering and Computer Science - Montefiore Institute ; Telim
DGTRE - Région wallonne. Direction générale des Technologies, de la Recherche et de l'Energie
DeepSport
Researchers ; Professionals
http://hdl.handle.net/2268/238475
Code will be available at
https://github.com/mistasse/ordinal-pooling-layers.

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Ordinal_Pooling.pdfAuthor preprint531.4 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.