کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6938905 | 1449966 | 2018 | 45 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Learning domain-shared group-sparse representation for unsupervised domain adaptation
ترجمه فارسی عنوان
نمایندگی مجزای گروهی به اشتراک گذاشته شده برای تطبیق دامنه بدون نظارت
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
انطباق دامنه، یادگیری فرهنگ لغت
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
In unsupervised domain adaptation, a key research problem is joint distribution alignment across the source and target domains. However, direct alignment of the source and target joint distributions is infeasible, because the target conditional distribution cannot be known without target labels. Instead of estimating target labels for target conditional distribution approximation, this paper proposes a new criterion of domain-shared group sparsity that is an equivalent condition for conditional distribution alignment. Together with marginal distribution alignment, we develop a domain-shared group-sparse dictionary learning model to learn domain-shared representations with aligned joint distributions. A cross-domain label propagation method is then proposed to train a classifier for the target domain using the domain-shared group-sparse representations and the target-specific information from the target data. The proposed method outperforms eight state-of-the-art unsupervised domain adaptation algorithms for cross-domain face recognition and cross-dataset object recognition with hand-drafted and deep features. Experimental results across multiple sub-domains show that the proposed method also performs well across datasets with large variance. Our results are quantitatively and qualitatively analyzed, and experiments of parameter sensitivity and convergence analysis are performed to show the effectiveness of the proposed method.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 81, September 2018, Pages 615-632
Journal: Pattern Recognition - Volume 81, September 2018, Pages 615-632
نویسندگان
Baoyao Yang, Andy J. Ma, Pong C. Yuen,