NDLI: Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains

Please wait, while we are loading the content...

Issue 1s(Special Issue on Smartphone-Based Interactive Technologies, Systems, and Applications and Special Issue on Extended Best Papers from ACM Multimedia 2014), October 2015

Issue 1, August 2015

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) : Volume 11

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) : Volume 10

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) : Volume 9

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) : Volume 8

Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains

Content Provider	ACM Digital Library
Author	Tang, Jinhui Li, Zechao Wang, Jingdong Shu, Xiangbo Qi, Guo-Jun
Copyright Year	2016
Description	Author Affiliation: University of Central Florida, Orlando, FL(Microsoft research asia, Beijing, P. R. China (Wang, Jingdong; Li, Zechao); Shu, Xiangbo; Nanjing university of science and technology, Nanjing, P.R. China (Tang, Jinhui; Qi, Guo-Jun))
Abstract	In recent years, deep neural networks have been successfully applied to model visual concepts and have achieved competitive performance on many tasks. Despite their impressive performance, traditional deep networks are subjected to the decayed performance under the condition of lacking sufficient training data. This problem becomes extremely severe for deep networks trained on a very small dataset, making them overfitting by capturing nonessential or noisy information in the training set. Toward this end, we propose a novel generalized deep transfer networks (DTNs), capable of transferring label information across heterogeneous domains, textual domain to visual domain. The proposed framework has the ability to adequately mitigate the problem of insufficient training images by bringing in rich labels from the textual domain. Specifically, to share the labels between two domains, we build parameter- and representation-shared layers. They are able to generate domain-specific and shared interdomain features, making this architecture flexible and powerful in capturing complex information from different domains jointly. To evaluate the proposed method, we release a new dataset extended from NUS-WIDE at http://imag.njust.edu.cn/NUS-WIDE-128.html. Experimental results on this dataset show the superior performance of the proposed DTNs compared to existing state-of-the-art methods.
Starting Page	1
Ending Page	22
Page Count	22
File Format	PDF
ISSN	15516857
e-ISSN	15516865
DOI	10.1145/2998574
Volume Number	12
Issue Number	4s
Journal	ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-11-18
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Heterogeneous-domain knowledge propagation Cross-domain label transfer Deep transfer network Image classification
Content Type	Text
Resource Type	Article
Subject	Hardware and Architecture Computer Networks and Communications

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation

Image label completion by pursuing contextual decomposability

Boosted Multifeature Learning for Cross-Domain Transfer

Two-level hierarchical feature learning for image classification

Fbufs: a high-bandwidth cross-domain transfer facility

Correspondence Autoencoders for Cross-Modal Retrieval

Deep autoencoder based domain adaptation for transfer learning.

Image classification based on convolutional neural networks with cross-level strategy

Generalized processor sharing with heterogeneous traffic classes

Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains

Similar Documents

Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation

Image label completion by pursuing contextual decomposability

Boosted Multifeature Learning for Cross-Domain Transfer

Two-level hierarchical feature learning for image classification

Fbufs: a high-bandwidth cross-domain transfer facility

Correspondence Autoencoders for Cross-Modal Retrieval

Deep autoencoder based domain adaptation for transfer learning.

Image classification based on convolutional neural networks with cross-level strategy

Generalized processor sharing with heterogeneous traffic classes

Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains