Available on ORBi since
31 July 2019
Paper published in a book (Scientific congresses and symposiums)
Ordinal Pooling
Deliège, Adrien  ; Istasse, Maxime; Kumar, Ashwani et al.
2020 • In 30th British Machine Vision Conference
Peer reviewed


Full Text
Author preprint (544.15 kB)

All documents in ORBi are protected by a user license.

Send to


Keywords :
pooling; convolutional neural network; deep learning; machine learning; ordinal pooling; downsampling
Abstract :
[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.
Research center :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
Disciplines :
Electrical & electronics engineering
Author, co-author :
Deliège, Adrien ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Istasse, Maxime
Kumar, Ashwani
De Vleeschouwer, Christophe
Van Droogenbroeck, Marc  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Language :
Title :
Ordinal Pooling
Publication date :
Event name :
British Machine Vision Conference (BMVC)
Event organizer :
British Machine Vision Association
Event place :
Cardiff, United Kingdom
Event date :
from 09-09-2019 to 12-09-2019
Audience :
Main work title :
30th British Machine Vision Conference
Peer reviewed :
Peer reviewed
Name of the research project :
Funders :
DGTRE - Région wallonne. Direction générale des Technologies, de la Recherche et de l'Énergie
Commentary :
Code will be available at https://github.com/mistasse/ordinal-pooling-layers.


Number of views
172 (11 by ULiège)
Number of downloads
185 (4 by ULiège)

Scopus citations®
Scopus citations®
without self-citations


Similar publications

Contact ORBi