Multipartite Pooling for Deep Convolutional Neural Networks
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 1 month ago.

Multipartite Pooling for Deep Convolutional Neural Networks
We propose a novel pooling strategy that learns how to adaptively rank deep convolutional features for selecting more informative representations. To this end, we exploit discriminative analysis to project the features onto a space spanned by the number of classes in the dataset under study. This maps the notion of labels in the feature space into instances in the projected space. We employ these projected distances as a measure to rank the existing features with respect to their specific discriminant power for each individual class. We then apply multipartite ranking to score the separability of the instances and aggregate oneversusall scores to compute an overall distinction score for each feature. For the pooling, we pick features with the highest scores in a pooling window instead of maximum, average or stochastic random assignments. Our experiments on various benchmarks confirm that the proposed strategy of multipartite pooling is highly beneficial to consistently improve the performance of deep convolutional networks via better generalization of the trained models for the testtime data.
Multipartite Pooling for Deep Convolutional Neural Networks
by Arash Shahriari, Fatih Porikli
https://arxiv.org/pdf/1710.07435v1.pdf
You must be logged in to reply to this topic.