Transferring knowledge fragments for learning distance metric from a heterogeneous domain
The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, we examine the problem of transfer distance metric learning (DML), which usually aims to mitigate the label information d...
Saved in:
Main Authors: | Luo, Yong, Wen, Yonggang, Liu, Tongliang, Tao, Dacheng |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Article |
語言: | English |
出版: |
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/141947 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Heterogeneous multitask metric learning across multiple domains
由: Luo, Yong, et al.
出版: (2020) -
Online multimodal distance metric learning with application to image retrieval
由: WU, Pengcheng, et al.
出版: (2013) -
Multi-label metric transfer learning jointly considering instance space and label space distribution divergence
由: Jiang, Siyu, et al.
出版: (2019) -
Learning Bregman distance functions for semi-supervised clustering
由: Wu, Lei, et al.
出版: (2012) -
Mining Social Images with Distance Metric Learning for Automated Image Tagging
由: WU, Pengcheng, et al.
出版: (2011)