Filters








63,487 Hits in 7.3 sec

Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation [article]

Qian Wang, Toby P. Breckon
2021 arXiv   pre-print
To address these issues, we propose a novel Cross-Domain Structure Preserving Projection (CDSPP) algorithm for HDA.  ...  Traditional domain adaptation algorithms assume that the representations of source and target samples reside in the same feature space, hence are likely to fail in solving the heterogeneous domain adaptation  ...  Figure 1 : 1 An illustration of the heterogeneous domain adaptation problem and our proposed approach using cross-domain structure preserving projection.  ... 
arXiv:2004.12427v3 fatcat:rx5dgopfjbhkxpf6eua3itxywy

Label Space Driven Heterogeneous Transfer Learning With Web Induced Alignment

Sanatan Sukhija
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We utilize the label relationships via web-distance to align the data of the domains in the projected space, while preserving the structure of the original data.  ...  Heterogeneous Transfer Learning (HTL) algorithms leverage knowledge from a heterogeneous source domain to perform a task in a target domain.  ...  Acknowledgment Narayanan Chatapuram Krishnan is the research adviser for this work.  ... 
doi:10.1609/aaai.v32i1.12166 fatcat:hu4nuqcacfcqhmrzi6usvcp3ke

Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment

Minying Zhang, Kai Liu, Yidong Li, Shihui Guo, Hongtao Duan, Yimin Long, Yi Jin
2021 AAAI Conference on Artificial Intelligence  
In this paper, we propose a coarse-tofine heterogeneous graph alignment (HGA) method to find cross-camera person matches by characterizing the unlabeled data as a heterogeneous graph for each camera.  ...  The proposed domain adaptation framework not only improves model generalization on target domain, but also facilitates mining and integrating the potential discriminative information across different cameras  ...  Acknowledgements This work is supported in part by the Fundamental Research Funds for the Central Universities of China under Grant 2019YJS032 and in part by the National Natural Science Foundation of  ... 
dblp:conf/aaai/ZhangLLGDLJ21 fatcat:6bjsjasfbzftrgiieuvknqdx6y

Heterogeneous Spectral-Spatial Feature Transfer with Structure Preserved Distribution Alignment for Hyperspectral Image Classification

Chongxiao Zhong, Junping Zhang, Qingle Guo, Ye Zhang
2022 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Then, in order to overcome the heterogeneity between the two feature sets, we build a structure preserved distribution alignment (SPDA) model to learn domain-specific projections to map the feature samples  ...  By performing MCSD, the spectral information and spatial structure information at different scales can be jointly adapted to learn transferable features for classification.  ...  On the other hand, the underlying cluster structures of inner-domain and cross-domain are both preserved in the projected feature space.  ... 
doi:10.1109/jstars.2022.3187757 fatcat:y4okvsqhsvfx3g46clf2st4kp4

Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning [article]

Jianglin Lu, Jie Zhou, Yudong Chen, Witold Pedrycz, Zhihui Lai, Kwok-Wai Hung
2022 arXiv   pre-print
As a result, they cannot be directly applied to heterogeneous cross-domain retrieval.  ...  Meanwhile, to alleviate negative transfer, the intrinsic geometrical structure of single-domain data is preserved by involving a domain affinity graph.  ...  interaction, which optimizes an adaptive bipartite graph for knowledge transfer and information fusion of cross-domain data; and c) domain structure preserving, which alleviates negative transfer by maintaining  ... 
arXiv:2206.12592v1 fatcat:vpef55hjl5bzvez7pyzawci6hi

Transfer Neural Trees for Heterogeneous Domain Adaptation [chapter]

Wei-Yu Chen, Tzu-Ming Harry Hsu, Yao-Hung Hubert Tsai, Yu-Chiang Frank Wang, Ming-Syan Chen
2016 Lecture Notes in Computer Science  
Heterogeneous domain adaptation (HDA) addresses the task of associating data not only across dissimilar domains but also described by different types of features.  ...  Moreover, to address semi-supervised HDA, a unique embedding loss term for preserving prediction and structural consistency between targetdomain data is introduced into TNT.  ...  To further handle heterogeneous cross-domain data, Shu et al. [28] presented a deep neural network structure, while co-occurrence cross-domain data are required for training their networks.  ... 
doi:10.1007/978-3-319-46454-1_25 fatcat:c47z35dy4nbt3l76cdqqmqmtei

Locality Preserving Joint Transfer for Domain Adaptation [article]

Li Jingjing and Jing Mengmeng and Lu Ke and Zhu Lei and Shen Heng Tao
2019 arXiv   pre-print
Notably, our approach is suitable for both homogeneous and heterogeneous domain adaptation by learning domain-specific projections.  ...  During the knowledge transfer, we also take the local consistency between samples into consideration, so that the manifold structures of samples can be preserved.  ...  So we perform four evaluations on Office+Caltech dataset for heterogeneous domain adaptation. The heterogeneous domain adaptation results of SURF to VGG-FC6 are reported in Table V .  ... 
arXiv:1906.07441v1 fatcat:2ontem74c5cvlo2qditieesx2u

Heterogeneous Domain Adaptation via Soft Transfer Network [article]

Yuan Yao, Yu Zhang, Xutao Li, Yunming Ye
2019 arXiv   pre-print
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain.  ...  In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for addressing the HDA problem.  ...  Wang and Mahadevan [41] propose a Domain Adaptation using Manifold Alignment (DAMA) to find projections by preserving both the topology of each domain and the discriminative structure. Duan et al.  ... 
arXiv:1908.10552v1 fatcat:owcelg242fhb5mbxxbjigijwpe

Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation

Yao-Hung Hubert Tsai, Yi-Ren Yeh, Yu-Chiang Frank Wang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
While domain adaptation (DA) aims to associate the learning tasks across data domains, heterogeneous domain adaptation (HDA) particularly deals with learning from cross-domain data which are of different  ...  With the goal of deriving a domain-invariant feature subspace for HDA, our CDLS is able to identify representative cross-domain data, including the unlabeled ones in the target domain, for performing adaptation  ...  Conclusion We proposed Cross-Domain Landmark Selection (CDLS) for performing heterogeneous domain adaptation (HDA).  ... 
doi:10.1109/cvpr.2016.549 dblp:conf/cvpr/TsaiYW16 fatcat:3b33il2enzfovdkghngcmhdwue

Unconstrained fuzzy feature fusion for heterogeneous unsupervised domain adaptation

Feng Liu, Guangquan Zhang, Jie Lu
2018 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)  
However, it is rarely discussed when the target domain is unlabeled and heterogeneous with the source domain, which is a very challenging problem in the domain adaptation field.  ...  Furthermore, the original information of the target domain is also preserved when reconstructing the features of the two domains.  ...  domain adaptation [6] ; 4) heterogeneous supervised domain adaptation [7] ; and 5) heterogeneous semi-supervised domain adaptation [8] .  ... 
doi:10.1109/fuzz-ieee.2018.8491633 dblp:conf/fuzzIEEE/Liu0L18 fatcat:jzuveujoefgmdkseqoq5zgck5q

HDA: Cross-Project Defect Prediction via Heterogeneous Domain Adaptation With Dictionary Learning

Zhou Xu, Peipei Yuan, Tao Zhang, Yutian Tang, Shuai Li, Zhen Xia
2018 IEEE Access  
INDEX TERMS Heterogeneous cross-project defect prediction, heterogeneous domain adaptation, dictionary learning.  ...  HDA treats the cross-project data as being from two different domains with heterogeneous feature sets.  ...  HETEROGENEOUS DOMAIN ADAPTATION Domain adaptation aims to transfer knowledge from a source domain to a different but related target domain.  ... 
doi:10.1109/access.2018.2873755 fatcat:hcavm4o3kfeirplahzz4pvbkue

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective [article]

Jing Zhang and Wanqing Li and Philip Ogunbona and Dong Xu
2019 arXiv   pre-print
This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.  ...  up for a possible solution accordingly.  ...  [224] propose the Cross-Domain Landmark Selection (CDLS) method for heterogeneous domain adaptation (HDA) using the statistical approach (MMD).  ... 
arXiv:1705.04396v3 fatcat:iknfmppi5zca7ljovdlwvdwluu

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition

Jing Zhang, Wanqing Li, Philip Ogunbona, Dong Xu
2019 ACM Computing Surveys  
This article takes a problem-oriented perspective and presents a comprehensive review of transferlearning methods, both shallow and deep, for cross-dataset visual recognition.  ...  This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.  ...  [224] propose the Cross-Domain Landmark Selection (CDLS) method for heterogeneous domain adaptation (HDA) using the statistical approach (MMD).  ... 
doi:10.1145/3291124 fatcat:thjzho3xsnfalprmkquldhwpvm

A survey on heterogeneous transfer learning

Oscar Day, Taghi M. Khoshgoftaar
2017 Journal of Big Data  
These can present significant challenges, as one must develop a method to bridge the feature spaces, data distributions, and other gaps which may be present in these cross-domain learning tasks.  ...  This paper contributes a comprehensive survey and analysis of current methods designed for performing heterogeneous transfer learning tasks to provide an updated, centralized outlook into current methodologies  ...  Consent for publication Not applicable. Ethics approval and consent to participate Not applicable. Funding Not applicable.  ... 
doi:10.1186/s40537-017-0089-0 fatcat:bpfjycwlkrawzdyyfv2ugle5cy

Bridging Heterogeneous Domains With Parallel Transport For Vision and Multimedia Applications

Raghuraman Gopalan
2016 Conference on Uncertainty in Artificial Intelligence  
Accounting for different feature types across datasets is a relatively under-studied problem in domain adaptation.  ...  We highlight the flexibility of our approach by accounting for multiple heterogeneous domains in training as well as in testing, and by considering the zero-shot domain transfer scenario where there are  ...  For this, instead of Step 1, we use outputs from existing heterogeneous adaptation techniques which map different dimensions onto a common one using more involved objectives related to domain structure  ... 
dblp:conf/uai/Gopalan16 fatcat:nst4cz5iknen3drf47u7k2j3y4
« Previous Showing results 1 — 15 out of 63,487 results