High-order local pooling and encoding Gaussians over a dictionary of Gaussians

Peihua Li, Hui Zeng, Qilong Wang, Chi Keung Simon Shiu, Lei Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

5 Citations (Scopus)

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.
Original languageEnglish
Article number7904668
Pages (from-to)3372-3384
Number of pages13
JournalIEEE Transactions on Image Processing
Volume26
Issue number7
DOIs
Publication statusPublished - 1 Jul 2017

Keywords

  • High-order local pooling (HO-LP)
  • Image classification
  • Manifold of Gaussians

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this