Please use this identifier to cite or link to this item:
Title: High-order local pooling and encoding gaussians over a dictionary of gaussians
Authors: Li, PH
Zeng, H 
Wang, QL
Shiu, SCK 
Zhang, L 
Keywords: Image classification
High-order local pooling (HO-LP)
Manifold of Gaussians
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on image processing, 2017, v. 26, no. 7, p. 3372-3384 How to cite?
Journal: IEEE transactions on image processing 
Abstract: Local pooling (LP) in configuration (feature) space proposed by Boureau et al. explicitly restricts similar features to be aggregated, which can preserve as much discriminative information as possible. At the time it appeared, this method combined with sparse coding achieved competitive classification results with only a small dictionary. However, its performance lags far behind the state-of-the-art results as only the zero-order information is exploited. Inspired by the success of high-order statistical information in existing advanced feature coding or pooling methods, we make an attempt to address the limitation of LP. To this end, we present a novel method called high-order LP (HO-LP) to leverage the information higher than the zero-order one. Our idea is intuitively simple: we compute the first-and second-order statistics per configuration bin and model them as a Gaussian. Accordingly, we employ a collection of Gaussians as visual words to represent the universal probability distribution of features from all classes. Our problem is naturally formulated as encoding Gaussians over a dictionary of Gaussians as visual words. This problem, however, is challenging since the space of Gaussians is not a Euclidean space but forms a Riemannian manifold. We address this challenge by mapping Gaussians into the Euclidean space, which enables us to perform coding with common Euclidean operations rather than complex and often expensive Riemannian operations. Our HO-LP preserves the advantages of the original LP: pooling only similar features and using a small dictionary. Meanwhile, it achieves very promising performance on standard benchmarks, with either conventional, hand-engineered features or deep learning-based features.
ISSN: 1057-7149
EISSN: 1941-0042
DOI: 10.1109/TIP.2017.2695884
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Feb 1, 2020


Last Week
Last month
Citations as of Feb 20, 2020

Page view(s)

Citations as of Feb 19, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.