Unsupervised and Semi-Supervised Robust Spherical Space Domain Adaptation

鉴别器 人工智能 模式识别(心理学) 计算机科学 分类器(UML) 领域(数学分析) 域适应 数学 电信 探测器 数学分析
作者
Xiang Gu,Jian Sun,Zongben Xu
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (3): 1757-1774 被引量:22
标识
DOI:10.1109/tpami.2022.3158637
摘要

Adversarial domain adaptation has been an effective approach for learning domain-invariant features by adversarial training. In this paper, we propose a novel adversarial domain adaptation approach defined in the spherical feature space, in which we define spherical classifier for label prediction and spherical domain discriminator for discriminating domain labels. In the spherical feature space, we develop a spherical robust pseudo-label loss to utilize pseudo-labels robustly, which weights the importance of the estimated labels of target domain data by the posterior probability of correct labeling, modeled by the Gaussian-uniform mixture model in the spherical space. Our proposed approach can be generally applied to both unsupervised and semi-supervised domain adaptation settings. In particular, to tackle the semi-supervised domain adaptation setting where a few labeled target domain data are available for training, we propose a novel reweighted adversarial training strategy for effectively reducing the intra-domain discrepancy within the target domain. We also present theoretical analysis for the proposed method based on the domain adaptation theory. Extensive experiments are conducted on multiple benchmarks for object recognition, digit recognition, and face recognition. The results show that our method either surpasses or is competitive compared with the recent methods for both unsupervised and semi-supervised domain adaptation. Ablation studies also confirm the effectiveness of the spherical classifier, spherical discriminator, spherical robust pseudo-label loss, and reweighted adversarial training strategy.
最长约 10秒,即可获得该文献文件

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
Shan发布了新的文献求助10
3秒前
桐桐应助xixiz1024采纳,获得10
4秒前
4秒前
6秒前
7秒前
SSSstriker完成签到,获得积分10
7秒前
nana完成签到 ,获得积分10
8秒前
9秒前
9秒前
老黑发布了新的文献求助10
11秒前
kinmke完成签到,获得积分10
14秒前
脑洞疼应助Shan采纳,获得10
14秒前
鳗鱼友琴发布了新的文献求助10
14秒前
wanci应助单纯的访冬采纳,获得10
17秒前
瑾沫流年完成签到,获得积分10
17秒前
21秒前
Cheung2121完成签到,获得积分20
24秒前
25秒前
Cheung2121发布了新的文献求助30
26秒前
单纯的访冬完成签到,获得积分10
26秒前
小月986完成签到,获得积分10
27秒前
大豆cong发布了新的文献求助30
27秒前
28秒前
30秒前
舒适念真发布了新的文献求助30
32秒前
梦nv孩完成签到,获得积分10
33秒前
南宫古伦完成签到 ,获得积分10
34秒前
俭朴夜香发布了新的文献求助10
37秒前
41秒前
Tiwiiw完成签到 ,获得积分10
42秒前
NexusExplorer应助大豆cong采纳,获得10
43秒前
杨震发布了新的文献求助30
47秒前
小蘑菇应助Oliver采纳,获得10
54秒前
56秒前
59秒前
1分钟前
Lucas应助m1采纳,获得10
1分钟前
在水一方应助jumbaumba采纳,获得10
1分钟前
疯狂的元风完成签到 ,获得积分10
1分钟前
1分钟前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
Encyclopedia of Geology (2nd Edition) 2000
Maneuvering of a Damaged Navy Combatant 650
Периодизация спортивной тренировки. Общая теория и её практическое применение 310
Mixing the elements of mass customisation 300
the MD Anderson Surgical Oncology Manual, Seventh Edition 300
Nucleophilic substitution in azasydnone-modified dinitroanisoles 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3780364
求助须知:如何正确求助?哪些是违规求助? 3325704
关于积分的说明 10224008
捐赠科研通 3040823
什么是DOI,文献DOI怎么找? 1669040
邀请新用户注册赠送积分活动 799013
科研通“疑难数据库(出版商)”最低求助积分说明 758648