Generalized Max Pooling

Naila Murray, Florent Perronnin; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 2473-2480


State-of-the-art patch-based image representations involve a pooling operation that aggregates statistics computed from local descriptors. Standard pooling operations include sum- and max-pooling. Sum-pooling lacks discriminability because the resulting representation is strongly influenced by frequent yet often uninformative descriptors, but only weakly influenced by rare yet potentially highly-informative ones. Max-pooling equalizes the influence of frequent and rare descriptors but is only applicable to representations that rely on count statistics, such as the bag-of-visual-words (BOV) and its soft- and sparse-coding extensions. We propose a novel pooling mechanism that achieves the same effect as max-pooling but is applicable beyond the BOV and especially to the state-of-the-art Fisher Vector-- hence the name Generalized Max Pooling (GMP). It involves equalizing the similarity between each patch and the pooled representation, which is shown to be equivalent to re-weighting the per-patch statistics. We show on five public image classification benchmarks that the proposed GMP can lead to significant performance gains with respect to heuristic alternatives.

Related Material

author = {Murray, Naila and Perronnin, Florent},
title = {Generalized Max Pooling},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}