DocumentCode :
3606576
Title :
DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning
Author :
Nguyen, Hien V. ; Huy Tho Ho ; Patel, Vishal M. ; Chellappa, Rama
Author_Institution :
Siemens Corp. Technol., Princeton, NJ, USA
Volume :
24
Issue :
12
fYear :
2015
Firstpage :
5479
Lastpage :
5491
Abstract :
Complex visual data contain discriminative structures that are difficult to be fully captured by any single feature descriptor. While recent work on domain adaptation focuses on adapting a single hand-crafted feature, it is important to perform adaptation of a hierarchy of features to exploit the richness of visual data. We propose a novel framework for domain adaptation using a sparse and hierarchical network (DASH-N). Our method jointly learns a hierarchy of features together with transformations that rectify the mismatch between different domains. The building block of DASH-N is the latent sparse representation. It employs a dimensionality reduction step that can prevent the data dimension from increasing too fast as one traverses deeper into the hierarchy. The experimental results show that our method compares favorably with the competing state-of-the-art methods. In addition, it is shown that a multi-layer DASH-N performs better than a single-layer DASH-N.
Keywords :
computer vision; learning (artificial intelligence); DASH-N; complex visual data; computer vision; data dimension; discriminative structures; feature learning; hand crafted feature; joint hierarchical domain adaptation; single feature descriptor; visual data; Computer vision; Dictionaries; Feature extraction; Object recognition; Testing; Training; Visualization; Domain adaptation; dictionary learning; hierarchical sparse representation; object recognition;
fLanguage :
English
Journal_Title :
Image Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1057-7149
Type :
jour
DOI :
10.1109/TIP.2015.2479405
Filename :
7273898
Link To Document :
بازگشت