Canonical Correlation Discriminative Learning for Domain Adaptation

2020 ◽  
pp. 567-580
Author(s):  
Wenjing Wang ◽  
Yuwu Lu ◽  
Zhihui Lai
Keyword(s):  
Canonical Correlation ◽  
Domain Adaptation ◽  
Discriminative Learning

Adapted discriminative coupled mappings for low-resolution face recognition with one-shot

2021 ◽  
pp. 1-15
Author(s):  
Yongjie Chu ◽  
Touqeer Ahmad ◽  
Lindu Zhao
Keyword(s):  
Face Recognition ◽  
Law Enforcement ◽  
High Resolution ◽  
Domain Adaptation ◽  
Face Image ◽  
Discriminative Learning ◽  
Low Resolution ◽  
Face Images ◽  
World Environment

Low-resolution face recognition with one-shot is a prevalent problem encountered in law enforcement, where it generally requires to recognize the low-resolution face images captured by surveillance cameras with the only one high-resolution profile face image in the database. The problem is very tough because the available samples is quite few and the quality of unknown images is quite low. To effectively address this issue, this paper proposes Adapted Discriminative Coupled Mappings (AdaDCM) approach, which integrates domain adaptation and discriminative learning. To achieve good domain adaptation performance for small size dataset, a new domain adaptation technique called Bidirectional Locality Matching-based Domain Adaptation (BLM-DA) is first developed. Then the proposed AdaDCM is formulated by unifying BLM-DA and discriminative coupled mappings into a single framework. AdaDCM is extensively evaluated on FERET, LFW, and SCface databases, which includes LR face images obtained in constrained, unconstrained, and real-world environment. The promising results on these datasets demonstrate the effectiveness of AdaDCM in LR face recognition with one-shot.

Integrating generalized domain adaptation and Fisher discriminative learning: A unified framework for face recognition with single sample per person

2021 ◽  
pp. 1-15
Author(s):  
Yongjie Chu ◽  
Lindu Zhao ◽  
Touqeer Ahmad
Keyword(s):  
Face Recognition ◽  
Domain Adaptation ◽  
Adaptation Effect ◽  
Single Sample ◽  
Discriminative Learning ◽  
Local Domain ◽  
Unified Framework ◽  
Target Domain ◽  
Model Learning ◽  
Single Sample Per Person

In this paper, an enhanced discriminative feature learning (EDFL) method is proposed to address single sample per person (SSPP) face recognition. With a separate auxiliary dataset, EDFL integrates Fisher discriminative learning and domain adaptation into a unified framework. The separate auxiliary dataset and the gallery/probe dataset are from two different domains (named source and target domains respectively) and have different data distributions. EDFL is modeled to transfer the discriminative knowledge learned from the source domain to the target domain for classification. Since the gallery set with SSPP contains scarce number of samples, it is hard to accurately represent the data distribution of the target domain, which hinders the adaptation effect. To overcome this problem, the generalized domain adaption (GDA) method is proposed to realize good overall domain adaptation when one domain contains limited samples. GDA considers the both global and local domain adaptation effect at the same time. Further, to guarantee that the learned domain adaptation components are optimal for discriminative learning, the domain adaptation and Fisher discriminant model learning are unified into a single framework and an efficient algorithm is designed to optimize them. The effectiveness of the proposed approach is demonstrated by extensive evaluation and comparison with some state-of-the-art methods.

Joint subspace and discriminative learning for self-paced domain adaptation

2020 ◽  
Vol 205 ◽  
pp. 106285
Author(s):  
Cheng Liu ◽  
Si Wu ◽  
Wenming Cao ◽  
Wenjun Shen ◽  
Dazhi Jiang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Discriminative Learning

Two-dimensional discriminative learning in the pigeon.

1968 ◽  
Vol 65 (3, Pt.1) ◽  
pp. 427-432 ◽  
Author(s):  
R. C. Gonzalez ◽  
M. E. Bitterman
Keyword(s):  
Discriminative Learning ◽  
Two Dimensional

Analysis of Maximum Expiratory Flow Volume Curves Using Canonical Correlation Analysis

1985 ◽  
Vol 24 (02) ◽  
pp. 91-100 ◽  
Author(s):  
W. van Pelt ◽  
Ph. H. Quanjer ◽  
M. E. Wise ◽  
E. van der Burg ◽  
R. van der Lende
Keyword(s):  
Correlation Analysis ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Flow Volume ◽  
Non Linear ◽  
Maximum Expiratory Flow ◽  
Expiratory Flow ◽  
Relationship Of ◽  
The Relationship ◽  
Age And Sex

SummaryAs part of a population study on chronic lung disease in the Netherlands, an investigation is made of the relationship of both age and sex with indices describing the maximum expiratory flow-volume (MEFV) curve. To determine the relationship, non-linear canonical correlation was used as realized in the computer program CANALS, a combination of ordinary canonical correlation analysis (CCA) and non-linear transformations of the variables. This method enhances the generality of the relationship to be found and has the advantage of showing the relative importance of categories or ranges within a variable with respect to that relationship. The above is exemplified by describing the relationship of age and sex with variables concerning respiratory symptoms and smoking habits. The analysis of age and sex with MEFV curve indices shows that non-linear canonical correlation analysis is an efficient tool in analysing size and shape of the MEFV curve and can be used to derive parameters concerning the whole curve.

Sign in / Sign up

Export Citation Format

Share Document