30,965 Hits in 5.2 sec

Semi-supervised Subspace Co-Projection for Multi-class Heterogeneous Domain Adaptation [chapter]

Min Xiao, Yuhong Guo
2015 Lecture Notes in Computer Science  
In this paper, we propose a novel semi-supervised subspace co-projection method to address multiclass heterogeneous domain adaptation.  ...  It also exploits the unlabeled data to promote the consistency of co-projected subspaces from the two domains based on a maximum mean discrepancy criterion.  ...  In this section, we present a semi-supervised subspace co-projection method to address heterogeneous multi-class domain adaptation under the setting described above.  ... 
doi:10.1007/978-3-319-23525-7_32 fatcat:f3zzanzenjd3lprdtifex6n7v4

Adaptive Consistency Regularization for Semi-Supervised Transfer Learning [article]

Abulikemu Abuduweili, Xingjian Li, Humphrey Shi, Cheng-Zhong Xu, Dejing Dou
2021 arXiv   pre-print
Results show that our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and FixMatch.  ...  In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain  ...  [47] introduced a semi-supervised domain adaptation method for semantic segmentation. [8] studied pseudo-labeling method on unsupervised domain adaptation for person re-identification.  ... 
arXiv:2103.02193v2 fatcat:efoyh2qo5zhypbflukcy5zxvhy

Cross Language Text Classification via Subspace Co-Regularized Multi-View Learning [article]

Yuhong Guo
2012 arXiv   pre-print
In this paper we develop a novel subspace co-regularized multi-view learning method for cross language text classification. This method is built on parallel corpora produced by machine translation.  ...  Our empirical study on a large set of cross language text classification tasks shows the proposed method consistently outperforms a number of inductive methods, domain adaptation methods, and multi-view  ...  , and feature augmentation methods, easyadapt (EA) (Daumé III, 2007) and its co-regularization based semi-supervised extension (EA++) (Daumé III et al., 2010) .  ... 
arXiv:1206.6481v1 fatcat:dmca2ynr7rbshoujg5akhvdpra

Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation

Yingda Xia, Dong Yang, Zhiding Yu, Fengze Liu, Jinzheng Cai, Lequan Yu, Zhuotun Zhu, Daguang Xu, Alan Yuille, Holger Roth
2020 Medical Image Analysis  
Semi-supervised learning and unsupervised domain adaptation both take the advantage of unlabeled data, and they are closely related to each other.  ...  Under unsupervised domain adaptation settings, we validate the effectiveness of this work by adapting our multi-organ segmentation model to two pathological organs from the Medical Segmentation Decathlon  ...  Unsupervised Domain Adaptation. Contrary to semi-supervised learning, domain adaptation problems often contain two datasets that have different distribution.  ... 
doi:10.1016/ pmid:32623276 fatcat:qtygh6is5vci3fv6oqep4yqcn4

Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation [article]

Ning Ma, Jiajun Bu, Lixian Lu, Jun Wen, Zhen Zhang, Sheng Zhou, Xifeng Yan
2021 arXiv   pre-print
Compared with state-of-the-art methods, the experimental results on three public datasets demonstrate that our method gets up to 19.9% improvements on semi-supervised adaptation tasks.  ...  In order to fully use the limited target data, a semi-supervised mutual enhancement method is proposed, in which entropy minimization and augmented label propagation are used iteratively to perform inter-domain  ...  Among these works, [17] proposed a co-regulation based approach for SSDA, based on the notion of augmented space.  ... 
arXiv:2107.06735v1 fatcat:qcp7dot73rg5tgxdxp66aah66q

Multi-level Consistency Learning for Semi-supervised Domain Adaptation [article]

Zizheng Yan, Yushuang Wu, Guanbin Li, Yipeng Qin, Xiaoguang Han, Shuguang Cui
2022 arXiv   pre-print
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain.  ...  Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains  ...  in label-scarce learning scenarios, e.g. domain adaptation, semi-supervised learning.  ... 
arXiv:2205.04066v1 fatcat:cdpql35gxbemzdxuzg5ts4kfji

Co-regularized Alignment for Unsupervised Domain Adaptation [article]

Abhishek Kumar and Prasanna Sattigeri and Kahini Wadhawan and Leonid Karlinsky and Rogerio Feris and William T. Freeman and Gregory Wornell
2018 arXiv   pre-print
We propose co-regularized domain alignment for unsupervised domain adaptation, which constructs multiple diverse feature spaces and aligns source and target distributions in each of them individually,  ...  The proposed method is generic and can be used to improve any domain adaptation method which uses domain alignment.  ...  Conclusion We proposed co-regularization based domain alignment for unsupervised domain adaptation.  ... 
arXiv:1811.05443v1 fatcat:v6zoum6rmnc7pjqwb7tpfolg7u

Semi-supervised Domain Adaptation for Semantic Segmentation [article]

Ying Chen, Xu Ouyang, Kaiyue Zhu, Gady Agam
2021 arXiv   pre-print
To cope with these limitations, both unsupervised domain adaptation (UDA) with full source supervision but without target supervision and semi-supervised learning (SSL) with partial supervision have been  ...  We propose a novel and effective two-step semi-supervised dual-domain adaptation (SSDDA) approach to address both cross- and intra-domain gaps in semantic segmentation.  ...  of our proposed approach to semi-supervised dual-domain adaptation for semantic segmentation.  ... 
arXiv:2110.10639v1 fatcat:fx2dojvzfbczvmpvwqhl2i6m2i

Semi-supervised Domain Adaptation with Instance Constraints

Jeff Donahue, Judy Hoffman, Erik Rodner, Kate Saenko, Trevor Darrell
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a general framework for adapting classifiers from "borrowed" data to the target domain using a combination of available labeled and unlabeled examples.  ...  We propose techniques that build on existing domain adaptation methods by explicitly modeling these relationships, and demonstrate empirically that they improve recognition accuracy in two scenarios, multicategory  ...  Finally, we showed how to extend the deformable parts model [12] to semi-supervised domain adaptation.  ... 
doi:10.1109/cvpr.2013.92 dblp:conf/cvpr/DonahueHRSD13 fatcat:ntqkgnsoqrarri4plassqhdsfq

KeCo: Kernel-Based Online Co-agreement Algorithm [chapter]

Laurens Wiel, Tom Heskes, Evgeni Levin
2015 Lecture Notes in Computer Science  
We propose a kernel-based online semi-supervised algorithm that is applicable for large scale learning tasks.  ...  In particular, we use a multi-view learning framework and a co-agreement strategy to take into account unlabelled data and to improve classification performance of the algorithm.  ...  The algorithm can operate in the semi-supervised regime by using co-regularization.  ... 
doi:10.1007/978-3-319-24282-8_26 fatcat:4tchsmtyere2tkdwxvdr4mhzyq

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  
Inspired by the recent advances of neural networks and deep learning, we propose Transfer Neural Trees (TNT) which jointly solves cross-domain feature mapping, adaptation, and classification in a NN-based  ...  Moreover, to address semi-supervised HDA, a unique embedding loss term for preserving prediction and structural consistency between targetdomain data is introduced into TNT.  ...  Based on the above observation, we propose to learn a novel NN-based framework in a semi-supervised HDA setting, without the need of co-occurrence training data pairs.  ... 
doi:10.1007/978-3-319-46454-1_25 fatcat:c47z35dy4nbt3l76cdqqmqmtei

Deep Semi-Supervised Learning for Time Series Classification [article]

Jann Goschenhofer, Rasmus Hvingelby, David Rügamer, Janek Thomas, Moritz Wagner, Bernd Bischl
2021 arXiv   pre-print
Based on these adaptations, we explore the potential of deep semi-supervised learning in the context of time series classification by evaluating our methods on large public time series classification problems  ...  While Semi-supervised learning has gained much attention in computer vision on image data, yet limited research exists on its applicability in the time series domain.  ...  Trees (Levatić et al., 2017) to inherently semi-supervised methods such as Label Propagation (Zhu & Ghahramani, 2002) , Manifold Regularization (Belkin et al., 2006) or Co-Training (Blum & Mitchell  ... 
arXiv:2102.03622v1 fatcat:t7arhdtrw5bz3lum7r7wgufygu

Consistency Regularization for Deep Face Anti-Spoofing [article]

Zezheng Wang, Zitong Yu, Xun Wang, Yunxiao Qin, Jiahong Li, Chenxu Zhao, Zhen Lei, Xin Liu, Size Li, Zhongyuan Wang
2021 arXiv   pre-print
Considering different application scenarios, we further design five diverse semi-supervised protocols to measure semi-supervised FAS techniques.  ...  Notably, our EPCR is free of annotations and can directly integrate into semi-supervised learning schemes.  ...  Despite success in general self-supervised and semi-supervised tasks, consistency regularization methods are still unexplored in FAS with serious domain shift and unknown attack issues.  ... 
arXiv:2111.12320v2 fatcat:oik4g2zonrbltaafhentv7ux6q

FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation [article]

Jaemin Na, Heechul Jung, Hyung Jin Chang, Wonjun Hwang
2021 arXiv   pre-print
However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies.  ...  Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress.  ...  Meanwhile, [44] addresses semi-supervised domain adaptation by breaking it down into SSL and UDA problems. Two models are in charge of each sub-problem and are trained based on co-teaching.  ... 
arXiv:2011.09230v2 fatcat:tp7mwwbmhnhyvjzc57qadvprl4

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

Ting Yao, Yingwei Pan, Chong-Wah Ngo, Houqiang Li, Tao Mei
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper proposes a novel domain adaptation framework, named Semi-supervised Domain Adaptation with Subspace Learning (SDASL), which jointly explores invariant lowdimensional structures across domains  ...  In many real-world applications, we are often facing the problem of cross domain learning, i.e., to borrow the labeled data or transfer the already learnt knowledge from a source domain to a target domain  ...  Semi-supervised domain adaptation methods have also been proposed. Jiang et al.  ... 
doi:10.1109/cvpr.2015.7298826 dblp:conf/cvpr/YaoPNLM15 fatcat:uxgbcxd2kfagtj5nknmsmuo234
« Previous Showing results 1 — 15 out of 30,965 results