intTypePromotion=1
zunia.vn Tuyển sinh 2024 dành cho Gen-Z zunia.vn zunia.vn
ADSENSE

Báo cáo khoa học: "Domain Adaptation by Constraining Inter-Domain Variability of Latent Feature Representation"

Chia sẻ: Hongdo_1 Hongdo_1 | Ngày: | Loại File: PDF | Số trang:10

44
lượt xem
4
download
 
  Download Vui lòng tải xuống để xem tài liệu đầy đủ

We consider a semi-supervised setting for domain adaptation where only unlabeled data is available for the target domain. One way to tackle this problem is to train a generative model with latent variables on the mixture of data from the source and target domains. Such a model would cluster features in both domains and ensure that at least some of the latent variables are predictive of the label on the source domain.

Chủ đề:
Lưu

Nội dung Text: Báo cáo khoa học: "Domain Adaptation by Constraining Inter-Domain Variability of Latent Feature Representation"

ADSENSE

CÓ THỂ BẠN MUỐN DOWNLOAD

 

Đồng bộ tài khoản
6=>0