%0 Generic %1 kumar2018ordinal %A Kumar, Ashwani %D 2018 %K cnn pooling %T Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps %U http://arxiv.org/abs/1804.02702 %X In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while completely discarding the information contained in other elements in a pooling region. To address this issue, a novel pooling scheme, Ordinal Pooling Network (OPN), is introduced in this work. OPN rearranges all the elements of a pooling region in a sequence and assigns different weights to these elements based upon their orders in the sequence, where the weights are learned via the gradient-based optimisation. The results of our small-scale experiments on image classification task demonstrate that this scheme leads to a consistent improvement in the accuracy over max-pooling operation. This improvement is expected to increase in deeper networks, where several layers of pooling become necessary.

@misc{kumar2018ordinal, abstract = {In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while completely discarding the information contained in other elements in a pooling region. To address this issue, a novel pooling scheme, Ordinal Pooling Network (OPN), is introduced in this work. OPN rearranges all the elements of a pooling region in a sequence and assigns different weights to these elements based upon their orders in the sequence, where the weights are learned via the gradient-based optimisation. The results of our small-scale experiments on image classification task demonstrate that this scheme leads to a consistent improvement in the accuracy over max-pooling operation. This improvement is expected to increase in deeper networks, where several layers of pooling become necessary.}, added-at = {2018-04-18T14:54:51.000+0200}, author = {Kumar, Ashwani}, biburl = {https://www.bibsonomy.org/bibtex/253bd220bd6739d040a0ab650c727fec1/rcb}, description = {[1804.02702] Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps}, interhash = {24eb25a34b6a710d9cf647b2d69159f6}, intrahash = {53bd220bd6739d040a0ab650c727fec1}, keywords = {cnn pooling}, note = {cite arxiv:1804.02702Comment: 9 pages with 4 figures}, timestamp = {2018-04-18T14:54:51.000+0200}, title = {Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps}, url = {http://arxiv.org/abs/1804.02702}, year = 2018 }