English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learnable Pooling Regions for Image Classification

Malinowski, M., & Fritz, M. (2013). Learnable Pooling Regions for Image Classification. In International Conference on Learning Representations Workshop Proceedings. Retrieved from http://arxiv.org/abs/1301.3516.

Item is

Files

show Files
hide Files
:
arXiv:1301.3516.pdf (Preprint), 424KB
Name:
arXiv:1301.3516.pdf
Description:
File downloaded from arXiv at 2014-03-21 12:00
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Malinowski, Mateusz1, Author           
Fritz, Mario1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG
 Abstract: Biologically inspired, from the early HMAX model to Spatial Pyramid Matching, pooling has played an important role in visual recognition pipelines. Spatial pooling, by grouping of local codes, equips these methods with a certain degree of robustness to translation and deformation yet preserving important spatial information. Despite the predominance of this approach in current recognition systems, we have seen little progress to fully adapt the pooling strategy to the task at hand. This paper proposes a model for learning task dependent pooling scheme -- including previously proposed hand-crafted pooling schemes as a particular instantiation. In our work, we investigate the role of different regularization terms showing that the smooth regularization term is crucial to achieve strong performance using the presented architecture. Finally, we propose an efficient and parallel method to train the model. Our experiments show improved performance over hand-crafted pooling schemes on the CIFAR-10 and CIFAR-100 datasets -- in particular improving the state-of-the-art to 56.29% on the latter.

Details

show
hide
Language(s): eng - English
 Dates: 2013-01-152013-08-062013
 Publication Status: Published online
 Pages: 10 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1301.3516
URI: http://arxiv.org/abs/1301.3516
BibTex Citekey: 758
 Degree: -

Event

show
hide
Title: International Conference on Learning Representations
Place of Event: Scottsdale, AZ, USA
Start-/End Date: 2013-05-02 - 2013-05-04

Legal Case

show

Project information

show

Source 1

show
hide
Title: International Conference on Learning Representations Workshop Proceedings
  Abbreviation : ICLR 2013
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: URI: http://openreview.net/venue/iclr2013