Sciweavers

Share
MM
2015
ACM

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

3 years 9 months ago
Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation
In recent years, deep networks have been successfully applied to model image concepts and achieved competitive performance on many data sets. In spite of impressive performance, the conventional deep networks can be subjected to the decayed performance if we have insufficient training examples. This problem becomes extremely severe for deep networks with powerful representation structure, making them prone to over fitting by capturing nonessential or noisy information in a small data set. In this paper, to address this challenge, we will develop a novel deep network structure, capable of transferring labeling information across heterogeneous domains, especially from text domain to image domain. This weaklyshared Deep Transfer Networks (DTNs) can adequately mitigate the problem of insufficient image training data by bringing in rich labels from the text domain. Specifically, we present a novel architecture of DTNs to translate cross-domain information from text to image. To share t...
Xiangbo Shu, Guo-Jun Qi, Jinhui Tang, Jingdong Wan
Added 14 Apr 2016
Updated 14 Apr 2016
Type Journal
Year 2015
Where MM
Authors Xiangbo Shu, Guo-Jun Qi, Jinhui Tang, Jingdong Wang
Comments (0)
books