Generalized Deep Transfer Networks For Knowledge Propagation In Heterogeneous Domains

Keywords

Algorithms; Cross-domain label transfer; Deep transfer network; Design; Experimentation; H.2.5 [database applications]: image representation; Heterogeneous-domain knowledge propagation; I.4.7 [learning]: parameter learning, concept learning, knowledge acquisition; Image classification; Performance

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.

Publication Date

11-1-2016

Publication Title

ACM Transactions on Multimedia Computing, Communications and Applications

Volume

12

Issue

4s

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1145/2998574

Socpus ID

84997194375 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84997194375

This document is currently not available here.

Share

COinS