English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 DetailsSummary
  Transfer Learning in a Transductive Setting

Rohrbach, M., Ebert, S., & Schiele, B. (2013). Transfer Learning in a Transductive Setting. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 26 (pp. 46-54). Red Hook, NY: Curran.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0017-EF91-0 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-D09F-8
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
http://papers.nips.cc/paper/5209-transfer-learning-in-a-transductive-setting.pdf (Any fulltext)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Rohrbach, Marcus1, Author           
Ebert, Sandra1, Author           
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: -
 Abstract: Category models for objects or activities typically rely on supervised learning requiring sufficiently large training sets. Transferring knowledge from known categories to novel classes with no or only a few labels however is far less researched even though it is a common scenario. In this work, we extend transfer learning with semi-supervised learning to exploit unlabeled instances of (novel) categories with no or only a few labeled instances. Our proposed approach Propagated Semantic Transfer combines three main ingredients. First, we transfer information from known to novel categories by incorporating external knowledge, such as linguistic or expert-specified information, e.g., by a mid-level layer of semantic attributes. Second, we exploit the manifold structure of novel classes. More specifically we adapt a graph-based learning algorithm - so far only used for semi-supervised learning - to zero-shot and few-shot learning. Third, we improve the local neighborhood in such graph structures by replacing the raw feature-based representation with a mid-level object- or attribute-based representation. We evaluate our approach on three challenging datasets in two different applications, namely on Animals with Attributes and ImageNet for image classification and on MPII Composites for activity recognition. Our approach consistently outperforms state-of-the-art transfer and semi-supervised approaches on all datasets.

Details

show
hide
Language(s): eng - English
 Dates: 20132013
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eSciDoc: escidoc:1835345
BibTex Citekey: escidoc:1835345
 Degree: -

Event

show
hide
Title: 27th Annual Conference on Neural Information Processing Systems
Place of Event: Lake Tahoe, NV, USA
Start-/End Date: 2013-12-05 - 2013-12-10

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 26
  Abbreviation : NIPS 2013
Source Genre: Proceedings
 Creator(s):
Burges, C. J. C.1, Editor
Bottou, L.1, Editor
Welling, M.1, Editor
Ghahramani, Z.1, Editor
Weinberger, K. Q.1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Red Hook, NY : Curran
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 46 - 54 Identifier: ISBN: 978-1-63266-024-4