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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, Noboru OHNISHI, "Incorporating Top-Down Guidance for Extracting Informative Patches for Image Classification" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 3, pp. 880-883, March 2012, doi: 10.1587/transinf.E95.D.880.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.880/_p
Copy
@ARTICLE{e95-d_3_880,
author={Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, Noboru OHNISHI, },
journal={IEICE TRANSACTIONS on Information},
title={Incorporating Top-Down Guidance for Extracting Informative Patches for Image Classification},
year={2012},
volume={E95-D},
number={3},
pages={880-883},
abstract={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.},
keywords={},
doi={10.1587/transinf.E95.D.880},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Incorporating Top-Down Guidance for Extracting Informative Patches for Image Classification
T2 - IEICE TRANSACTIONS on Information
SP - 880
EP - 883
AU - Shuang BAI
AU - Tetsuya MATSUMOTO
AU - Yoshinori TAKEUCHI
AU - Hiroaki KUDO
AU - Noboru OHNISHI
PY - 2012
DO - 10.1587/transinf.E95.D.880
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2012
AB - 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.
ER -