Generalized Max Pooling

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 2473 - 2480
• Main Authors: Murray, Naila, Perronnin, Florent
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Birds; classification; Computer vision; Encoding; image representations; Kernel; Mathematical analysis; Pattern recognition; pooling; Representations; Similarity; State of the art; Statistics; Vectors; Visualization
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2014.317

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.