Change search
ReferencesLink to record
Permanent link

Direct link
Interactive Learning with Convolutional Neural Networks for Image Labeling
Örebro University, School of Science and Technology, Örebro University, Sweden. (AASS)ORCID iD: 0000-0002-0579-7181
Örebro University, School of Science and Technology, Örebro University, Sweden. (AASS)
Örebro University, School of Science and Technology, Örebro University, Sweden. (AASS)ORCID iD: 0000-0002-0305-3728
Örebro University, School of Science and Technology, Örebro University, Sweden. (AASS)ORCID iD: 0000-0002-3122-693X
2016 (English)In: International Joint Conference on Artificial Intelligence (IJCAI), 2016Conference paper, Poster (Refereed)
Abstract [en]

Recently, deep learning models, such as Convolutional Neural Networks, have shown to give good performance for various computer vision tasks. A pre-requisite for such models is to have access to lots of labeled data since the most successful ones are trained with supervised learning. The process of labeling data is expensive, time-consuming, tedious, and sometimes subjective, which can result in falsely labeled data, which has a negative effect on both the training and the validation. In this work, we propose a human-in-the-loop intelligent system that allows the agent and the human to collabo- rate to simultaneously solve the problem of labeling data and at the same time perform scene labeling of an unlabeled image data set with minimal guidance by a human teacher. We evaluate the proposed in- teractive learning system by comparing the labeled data set from the system to the human-provided labels. The results show that the learning system is capable of almost completely label an entire image data set starting from a few labeled examples provided by the human teacher.

Place, publisher, year, edition, pages
2016.
National Category
Computer Science
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-52116OAI: oai:DiVA.org:oru-52116DiVA: diva2:968110
Conference
International Joint Conference on Artificial Intelligence (IJCAI), New York, USA, 9-15th July, 2016
Available from: 2016-09-12 Created: 2016-09-12 Last updated: 2016-09-21Bibliographically approved

Open Access in DiVA

fulltext(1435 kB)14 downloads
File information
File name FULLTEXT01.pdfFile size 1435 kBChecksum SHA-512
cd2689a209a427e3ad4a8d90ac1748b49f13ba264e2ddc86d56e8e1e644dca024ac089f9e000a1098298113681693e38773b02d6aeb05a26b64a0cd4fd03ee35
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Längkvist, MartinAlirezaie, MarjanKiselev, AndreyLoutfi, Amy
By organisation
School of Science and Technology, Örebro University, Sweden
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 14 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 13 hits
ReferencesLink to record
Permanent link

Direct link