Constrained Deep Transfer Feature Learning and its Applications

作者
Yue Wu,Qiang Ji
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.1709.08128
摘要

Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from the source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as a constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
六十分万岁完成签到,获得积分10
1秒前
打折便当吃中毒完成签到,获得积分10
2秒前
愉快的真发布了新的文献求助10
2秒前
4秒前
Xjq3619发布了新的文献求助10
4秒前
狸花猫发布了新的文献求助10
5秒前
狂野的月光完成签到 ,获得积分20
9秒前
Kao应助唐科采纳,获得10
10秒前
11秒前
勤奋世界完成签到,获得积分20
11秒前
杨一关注了科研通微信公众号
11秒前
水母完成签到,获得积分10
11秒前
ygdkb完成签到,获得积分10
13秒前
Ava应助吾日三省吾身采纳,获得10
14秒前
liangfulove完成签到,获得积分10
15秒前
勤奋世界发布了新的文献求助10
15秒前
羡鱼完成签到,获得积分10
17秒前
Emper完成签到,获得积分10
18秒前
18秒前
温柔如南完成签到,获得积分10
19秒前
wyz完成签到,获得积分10
20秒前
慕青应助杨一采纳,获得50
25秒前
几米的漫画99完成签到,获得积分20
25秒前
小黑米发布了新的文献求助10
25秒前
充电宝应助无语的怜梦采纳,获得10
26秒前
可爱的函函应助真人采纳,获得10
27秒前
轻松秋荷完成签到,获得积分10
31秒前
NexusExplorer应助李兴采纳,获得10
32秒前
脑洞疼应助Derris采纳,获得10
33秒前
dp完成签到,获得积分10
33秒前
33秒前
35秒前
情怀应助吾日三省吾身采纳,获得10
35秒前
36秒前
青葱加鱼块完成签到,获得积分10
37秒前
37秒前
真人发布了新的文献求助10
39秒前
39秒前
naa发布了新的文献求助10
40秒前
zzx关闭了zzx文献求助
41秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Markov Chain Monte Carlo 5000
Weaponeering: An Introduction Fourth Edition, Volume 1 1000
Advanced Weaponeering Fourth Edition, Volume 2 1000
Evidence Summary. Injection (subcutaneous):op- timal administration 1000
悉尼大学博士学位论文,题目:Modelling and testing of one-sided stitched laminated composites. 作者:Kristopher P. Plain 700
Matrix Methods in Data Mining and Pattern Recognition Second Edition 610
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7493841
求助须知:如何正确求助?哪些是违规求助? 9085425
关于积分的说明 19376833
捐赠科研通 7105840
什么是DOI,文献DOI怎么找? 3249627
关于科研通互助平台的介绍 2419090
邀请新用户注册赠送积分活动 2235297