Incorporating Top-Down Guidance for Extracting Informative Patches for Image Classification

Shuang BAI  Tetsuya MATSUMOTO  Yoshinori TAKEUCHI  Hiroaki KUDO  Noboru OHNISHI 

Publication
IEICE TRANSACTIONS on Information and Systems  Vol.E95-D  No.3  pp.880-883
Publication Date: 2012/03/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Pattern Recognition
Keyword: 
patch sampling,  informative regions,  image classification, 

Full Text: PDF(612.9KB)

Summary: 
In this letter, we introduce a novel patch sampling strategy for the task of image classification, which is fundamentally different from current patch sampling strategies. A top-down guidance learned from training images is used to guide patch sampling towards informative regions. Experiment results show that this approach achieved noticeable improvement over baseline patch sampling strategies for the classification of both object categories and scene categories.