6,500 Hits in 4.7 sec

A Comparative Study on Unsupervised Domain Adaptation Approaches for Coffee Crop Mapping [article]

Edemir Ferreira, Mário S. Alvim, Jefersson A. dos Santos
2018 arXiv   pre-print
In this work, we investigate the application of existing unsupervised domain adaptation (UDA) approaches to the task of transferring knowledge between crop regions having different coffee patterns.  ...  However, UDA methods may lead to negative transfer, which may indicate that domains are too different that transferring knowledge is not appropriate.  ...  Ideally, we would like to learn a proper domain adaptation in an unsupervised manner.  ... 
arXiv:1806.02400v1 fatcat:hgnr5k7zeffalojml2ky5wz4ay

Category-Sensitive Domain Adaptation for Land Cover Mapping in Aerial Scenes

Bo Fang, Rong Kou, Li Pan, Pengfei Chen
2019 Remote Sensing  
As an efficient solution for this issue, domain adaptation has been widely utilized in numerous semantic labeling-based applications.  ...  adaptation (CsDA) method for land cover mapping using very-high-resolution (VHR) optical aerial images.  ...  [39] proposed for supervised domain adaptation with paired images, while Zhu et al. [18] p for unsupervised domain adaptation with unpaired images.  ... 
doi:10.3390/rs11222631 fatcat:gbkmgj7qe5dhjmg44uiqptghbu

Unsupervised Alignment of Distributional Word Embeddings [article]

Ais̈satou Diallo
2022 arXiv   pre-print
In this paper, we propose stochastic optimization approach for aligning probabilistic embeddings.  ...  Finally, we evaluate our method on the problem of unsupervised word translation, by aligning word embeddings trained on monolingual data.  ...  Acknowledgments This work has been supported by the German Research Foundation as part of the Research Training Group Adaptive Preparation of Information from Heterogeneous Sources (AIPHES) under grant  ... 
arXiv:2203.04863v1 fatcat:zqltrlwnqzgnxbnk5wmq4os6su

Unsupervised Domain Adaptive Graph Convolutional Networks

Man Wu, Shirui Pan, Chuan Zhou, Xiaojun Chang, Xingquan Zhu
2020 Proceedings of The Web Conference 2020  
In this paper, we present a novel approach, unsupervised domain adaptive graph convolutional networks (UDA-GCN), for domain adaptation learning for graphs.  ...  However, most GCNs only work in a single domain (graph) incapable of transferring knowledge from/to other domains (graphs), due to the challenges in both graph representation learning and domain adaptation  ...  In this paper, we presented a novel unsupervised domain adaptive graph convolutional networks (UDA-GCN) to enable knowledge adaptation between graphs.  ... 
doi:10.1145/3366423.3380219 dblp:conf/www/WuP0CZ20 fatcat:5rrk25dpd5advc5daunmm4oyza

Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment [article]

Alex Gabourie, Mohammad Rostami, Philip Pope, Soheil Kolouri, Kyungnam Kim
2019 arXiv   pre-print
We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target  ...  To mitigate the challenge of class matching, we also align corresponding classes in the embedding space by using high confidence pseudo-labels for the target domain, i.e. assigning the class for which  ...  Fig. 1 : 1 Architecture of the proposed unsupervised domain adaptation framework.  ... 
arXiv:1907.02271v2 fatcat:2ct3ilhgenetlmtqncjylk5nxm

Spatial-Aware GAN for Unsupervised Person Re-identification [article]

Fangneng Zhan, Changgong Zhang
2021 arXiv   pre-print
Unsupervised domain adaptation (UDA) has been investigated to mitigate this constraint, but most existing systems adapt images at pixel level only and ignore obvious discrepancies at spatial level.  ...  A novel disentangled cycle-consistency loss is designed which guides the learning of spatial-level and pixel-level adaptation in a collaborative manner.  ...  One typical strategy to tackle domain shift and bias is Unsupervised Domain Adaptation (UDA) which aims to transfer the learned knowledge from a labeled source domain to an unlabeled target domain.  ... 
arXiv:1911.11312v2 fatcat:5ujkfqunjjfornlzj7xvqdwf74

Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning [article]

Shaoxiong Ji and Teemu Saravirta and Shirui Pan and Guodong Long and Anwar Walid
2021 arXiv   pre-print
Specifically, we explore various learning algorithms to improve the vanilla federated averaging algorithm and review model fusion methods such as adaptive aggregation, regularization, clustered methods  ...  emerging trends, we also discuss federated learning in the intersection with other learning paradigms, termed as federated x learning, where x includes multitask learning, meta-learning, transfer learning, unsupervised  ...  Fully unsupervised data can be enhanced via domain adaption, where the aim is to transfer knowledge from a labeled domain to an unlabeled one. Taxonomy.  ... 
arXiv:2102.12920v2 fatcat:5fcwfhxibbedbcbuzrfyqdedky

Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint [article]

Jiawei Chen and Yuexiang Li and Kai Ma and Yefeng Zheng
2021 arXiv   pre-print
The proposed Mutual-GAN adopts mutual information constraint to preserve image-objects during cross-weather adaptation, which is an unsolved problem for most unsupervised image-to-image translation approaches  ...  Convolutional neural network (CNN) have proven its success for semantic segmentation, which is a core task of emerging industrial applications such as autonomous driving.  ...  recently proposed GAN for imagebased domain adaptation, i.e., AugGAN [15] , is not involved for comparison, due to the strong prior-knowledge (pixel-wise annotation) used in the approach.  ... 
arXiv:2106.16000v1 fatcat:wwjxeu5obnd2vhumi55r77kroq

RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation [article]

Adriano Cardace, Riccardo Spezialetti, Pierluigi Zama Ramirez, Samuele Salti, Luigi Di Stefano
2021 arXiv   pre-print
Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations.  ...  on both domains; ii) a novel self-training protocol that learns domain-specific decision boundaries and reduces the negative impact of mislabelled target samples and in-domain intra-class variability.  ...  Acknowledgment The authors would like to thank Injenia Srl for supporting this research.  ... 
arXiv:2110.11036v1 fatcat:rror4ona5nh3pag2l7qrilqpme

DiReT: An effective discriminative dimensionality reduction approach for multi-source transfer learning

J. Tahmoresnezhad, S. Hashemi
2017 Scientia Iranica. International Journal of Science and Technology  
Moreover, DiReT employs multiple source domains and semi-supervised target domain to transfer knowledge from multiple resources, and it also bridges across source and target domains to nd common knowledge  ...  KEYWORDS Multi-source transfer learning; Domain adaptation; Discriminative dimensionality reduction; Fisher discriminant analysis. Abstract.  ...  In unsupervised domain adaptation, no label is available in target domain. Blitzer et al.  ... 
doi:10.24200/sci.2017.4113 fatcat:el3vzjxe3nf4vcnlvdvyn6hdvi

Transductive Domain Adaptation with Affinity Learning

Le Shu, Longin Jan Latecki
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
We study the problem of domain adaptation, which aims to adapt the classifiers trained on a labeled source domain to an unlabeled target domain.  ...  We propose a novel method to solve domain adaptation task in a transductive setting.  ...  CONCLUSIONS We propose a novel transductive domain adaptation method. Empirical results clearly demonstrate that it outperforms state-of-the-art methods.  ... 
doi:10.1145/2806416.2806643 dblp:conf/cikm/ShuL15 fatcat:ld3c5iu6wrhpfgrmpy74xgjjay

Unsupervised Deep Feature Transfer for Low Resolution Image Classification [article]

Yuanwei Wu, Ziming Zhang, Guanghui Wang
2019 arXiv   pre-print
We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer.  ...  In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method.  ...  [24] propose a deep adaptation network architecture to match the mean embeddings of different domain distributions in a reproducing kernel Hilbert space. Guo et al.  ... 
arXiv:1908.10012v2 fatcat:3eyozf2fpbgonaf7flqa4bsehm

Multi-domain Adaptation in Brain MRI Through Paired Consistency and Adversarial Learning [chapter]

Mauricio Orbes-Arteaga, Thomas Varsavsky, Carole H. Sudre, Zach Eaton-Rosen, Lewis J. Haddow, Lauge Sørensen, Mads Nielsen, Akshay Pai, Sébastien Ourselin, Marc Modat, Parashkev Nachev, M. Jorge Cardoso
2019 Lecture Notes in Computer Science  
The proposed method significantly outperforms other domain adaptation baselines.  ...  Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source domain to perform well on an unlabeled target domain.  ...  domain adaptation [13] as well as an unsupervised baseline for WMH segmentation.  ... 
doi:10.1007/978-3-030-33391-1_7 pmid:34109324 pmcid:PMC7610933 fatcat:nfvxm6muvfcn7c6hsv3trl3dry

Heterogeneous Transfer Learning: An Unsupervised Approach [article]

Feng Liu, Guanquan Zhang, Jie Lu
2018 arXiv   pre-print
The unsupervised knowledge transfer theorem sets out the transfer conditions necessary to prevent negative transfer.  ...  Transfer learning leverages the knowledge in one domain, the source domain, to improve learning efficiency in another domain, the target domain.  ...  ), and unsupervised domain adaptation (HeUDA).  ... 
arXiv:1701.02511v4 fatcat:annryoyrp5h6dggjnlzn4mcm7y

GRAFT: Unsupervised Adaptation to Resizing for Detection of Image Manipulation

Ludovic Darmet, Kai Wang, Francois Cayre
2020 IEEE Access  
Adaptation is performed in an unsupervised fashion, i.e., without using any ground-truth label in the pre-resized testing domain, for the detection of image manipulation on very small patches.  ...  We propose a new and effective adaptation method for one state-of-the-art image manipulation detection pipeline, and we call our proposed method Gaussian mixture model Resizing Adaptation by Fine-Tuning  ...  Patrick Bas for the discussions on cover-source mismatch for steganalysis [4] and Dr. Pedro Rodrigues for inspiring discussions about his work on Riemannian geometry [25] .  ... 
doi:10.1109/access.2020.2980992 fatcat:ucx37j3pxfeenmlvyqz3mzodje
« Previous Showing results 1 — 15 out of 6,500 results