A boosting approach to learning receptive fields for scene categorization
- 1 September 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2013 IEEE International Conference on Image Processing
Abstract
Recently, sparse coding-based algorithms have achieved high performance on several popular scene classification benchmarks. Yet extensive efforts along this direction focus on strategies for coding and dictionary learning, few works have addressed the problem of optimal pooling regions selection. In this work, we show that the Viola-Jones algorithm, which is well-known in face detection, can be tailored to learning receptive fields for the sparse coding algorithms. Specifically, using the boosting approach to receptive field learning, image/scene categorization performance can be ubiquitously enhanced on several benchmarks (UIUC sport event, 15 natural scenes and the Caltech 101 dataset) to the state-of-the-art, using only low dimensional features and small codebook sizes. Furthermore, the “salient pooling regions” can be obtained explicitly.Keywords
This publication has 17 references indexed in Scilit:
- Locality-constrained and spatially regularized coding for scene categorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Image Classification by Hierarchical Spatial Pooling with Partial Least Squares AnalysisPublished by British Machine Vision Association and Society for Pattern Recognition ,2012
- Ask the locals: Multi-way local pooling for image recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Local features are not lonely – Laplacian sparse coding for image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural imagesVision Research, 2001
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)The Annals of Statistics, 2000
- Improved Boosting Algorithms Using Confidence-rated PredictionsMachine Learning, 1999
- A desicion-theoretic generalization of on-line learning and an application to boostingLecture Notes in Computer Science, 1995