Regularized Max Pooling for Image Categorization
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.32
Abstract
We propose Regularized Max Pooling (RMP) for image classification. RMP classifies an image (or an image region) by extracting feature vectors at multiple subwindows at multiple locations and scales. Unlike Spatial Pyramid Matching where the subwindows are defined purely based on geometric correspondence, RMP accounts for the deformation of discriminative parts. The amount of deformation and the discriminative ability for multiple parts are jointly learned during training. RMP outperforms the state-of-the-art performance by a wide margin on the challenging PASCAL VOC2012 dataset for human action recognition on still images.
Session
Image Classification
Files

Presentation
Citation
Minh Hoai. Regularized Max Pooling for Image Categorization. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.32 title = {Regularized Max Pooling for Image Categorization}, author = {Hoai, Minh}, year = {2014}, booktitle = {Proceedings of the British Machine Vision Conference}, publisher = {BMVA Press}, editors = {Valstar, Michel and French, Andrew and Pridmore, Tony} doi = { http://dx.doi.org/10.5244/C.28.32 } }