English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Optimizing one-shot recognition with micro-set learning

Tang, K., Tappen, M., Sukthankar, R., & Lampert, C. (2010). Optimizing one-shot recognition with micro-set learning. In Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010) (pp. 3027-3034). Piscataway, NJ, USA: IEEE.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-81E6-8 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-81E7-7
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Tang, KD, Author
Tappen, MF, Author
Sukthankar , R, Author
Lampert, CH1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: For object category recognition to scale beyond a small number of classes, it is important that algorithms be able to learn from a small amount of labeled data per additional class. One-shot recognition aims to apply the knowledge gained from a set of categories with plentiful data to categories for which only a single exemplar is available for each. As with earlier efforts motivated by transfer learning, we seek an internal representation for the domain that generalizes across classes. However, in contrast to existing work, we formulate the problem in a fundamentally new manner by optimizing the internal representation for the one-shot task using the notion of micro-sets. A micro-set is a sample of data that contains only a single instance of each category, sampled from the pool of available data, which serves as a mechanism to force the learned representation to explicitly address the variability and noise inherent in the one-shot recognition task. We optimize our learned domain features so that they minimize an expected loss over micro-sets drawn from the training set and show that these features generalize effectively to previously unseen categories. We detail a discriminative approach for optimizing one-shot recognition using micro-sets and present experiments on the Animals with Attributes and Caltech-101 datasets that demonstrate the benefits of our formulation.

Details

show
hide
Language(s):
 Dates: 2010-06
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1109/CVPR.2010.5540053
 Degree: -

Event

show
hide
Title: Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)
Place of Event: San Francisco, CA , USA
Start-/End Date: 2010-06-13 - 2010-06-18

Legal Case

show

Project information

show

Source 1

show
hide
Title: Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 3027 - 3034 Identifier: ISBN: 978-1-4244-6984-0