Filters








64,353 Hits in 2.6 sec

Semi-supervised Domain Adaptive Structure Learning [article]

Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu
2021 arXiv   pre-print
Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples.  ...  Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.  ...  Index Terms-Semi-supervised Domain Adaptation, Multiviews, Self-training, Adaptive Structure Learning I.  ... 
arXiv:2112.06161v1 fatcat:apzijyrajfdpzcglxpkalahmzu

Contradictory Structure Learning for Semi-supervised Domain Adaptation [article]

Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu
2021 arXiv   pre-print
To solve these challenges, we propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures (UODA).  ...  Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary  ...  Unity of Opposite Structure Learning Apart from learning robust decision boundaries relying on domain based classifiers, we propose the Unity of Opposite Structure Learning for Semi-supervised Domain Adaptation  ... 
arXiv:2002.02545v2 fatcat:xvyot7yg3nffterwvccmf2xyme

Learning from partially labeled data

Siamak Mehrkanoon, Xiaolin Huang, Johan A. K. Suykens
2020 The European Symposium on Artificial Neural Networks  
In particular, in this context one can refer to semi-supervised modelling, transfer learning, domain adaptation and multi-view learning among others.  ...  Designing models that can learn from partially labeled data, or leveraging labeled data in one domain and unlabeled data in a different but related domain is of great interest in many applications.  ...  The semi-supervised learning, domain adaption, multi-view learning are among existing proposed models. Semi-supervised models use both labeled and unlabeled data points in the learning process.  ... 
dblp:conf/esann/MehrkanoonHS20 fatcat:hdjcnwwu4fgzbjwv5uotkcyvua

Domain Adaptation with Adversarial Training and Graph Embeddings [article]

Firoj Alam and Shafiq Joty and Muhammad Imran
2018 arXiv   pre-print
We propose a novel model that performs adversarial learning based domain adaptation to deal with distribution drifts and graph based semi-supervised learning to leverage unlabeled data within a single  ...  unified deep learning framework.  ...  Related Work Two lines of research are directly related to our work: (i) semi-supervised learning and (ii) domain adaptation. Several models have been proposed for semi-supervised learning.  ... 
arXiv:1805.05151v1 fatcat:7rj47d6zlvcedkdvv4j46ekz2a

Domain Adaptation with Adversarial Training and Graph Embeddings

Firoj Alam, Shafiq Joty, Muhammad Imran
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We propose a novel model that performs adversarial learning based domain adaptation to deal with distribution drifts and graph based semi-supervised learning to leverage unlabeled data within a single  ...  unified deep learning framework.  ...  Related Work Two lines of research are directly related to our work: (i) semi-supervised learning and (ii) domain adaptation. Several models have been proposed for semi-supervised learning.  ... 
doi:10.18653/v1/p18-1099 dblp:conf/acl/JotyAI18 fatcat:fy5l3zyaare4np6xxesl7476ye

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data [article]

Jun Chen, Heye Zhang, Raad Mohiaddin, Tom Wong, David Firmin, Jennifer Keegan, Guang Yang
2021 arXiv   pre-print
Generalising semi-supervised learning to cross-domain data is of high importance to further improve model robustness.  ...  In this study, we alleviate these problems by proposing an Adaptive Hierarchical Dual Consistency (AHDC) for the semi-supervised LA segmentation on cross-domain data.  ...  Semi-supervised Learning Semi-supervised learning alleviates the problem of the lack of labelled data. Here we only discuss related consistencybased and disagreement-based semi-supervised learning.  ... 
arXiv:2109.08311v2 fatcat:6pxfl7tv45b5hg2bhal3qp3mbq

SSL-QA: Analysis of Semi-Supervised Learning for QuestionAnswering

Parth Patel, Jignesh Prajapati
2017 IOSR Journal of Computer Engineering  
In this paper we analyse different intensive researches in semi-supervised learning for question-answering.  ...  Open domain natural language question answering (QA) is a process of automatically finding answers to questions searching collections of text files.  ...  We show that semi-supervise learning algorithm for why question-answering, QA through transfer learning, QA with generative domain adaptive nets.  ... 
doi:10.9790/0661-1903051415 fatcat:iv2qx3pejjf7fkt5rsewld7dky

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  
Moreover, to address semi-supervised HDA, a unique embedding loss term for preserving prediction and structural consistency between targetdomain data is introduced into TNT.  ...  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  ...  [24] presented the approach of semi-supervised domain adaptation with subspace learning (SDASL), which minimizes the prediction risk while preserving the locality structure and manifold information  ... 
doi:10.1007/978-3-319-46454-1_25 fatcat:c47z35dy4nbt3l76cdqqmqmtei

Adversarial Learning based Discriminative Domain Adaptation for Geospatial Image Analysis

Nikhil Makkar, Hsiuhan Lexie Yang, Saurabh Prasad
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
First, we approached the problem of unavailable target domain labels with unsupervised domain adaptation and then extended our method for semi-supervised domain adaptation to use a few available labels  ...  In this work, we use adversarial learning for domain adaptation for remote sensing applications.  ...  Semi-supervised Domain Adaptation the semi-supervised domain adaptation, we use noadaptation results as our baseline, which was obtained by training a similar deep learning network on pre-trained source  ... 
doi:10.1109/jstars.2021.3132259 fatcat:5ppi25cwirc2bmnlgolauiwga4

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data

Jun Chen, Heye Zhang, Raad Mohiaddin, Tom Wong, David Firmin, Jennifer Keegan, Guang Yang
2021 IEEE Transactions on Medical Imaging  
Generalising semi-supervised learning to cross-domain data is of high importance to further improve model robustness.  ...  In this study, we alleviate these problems by proposing an Adaptive Hierarchical Dual Consistency (AHDC) for the semi-supervised LA segmentation on cross-domain data.  ...  semi-supervised learning. 808 VII.  ... 
doi:10.1109/tmi.2021.3113678 pmid:34534077 fatcat:3clzcy7e4ngr3e5hhfnkcnysoi

StyHighNet: Semi-Supervised Learning Height Estimation from a Single Aerial Image via Unified Style Transferring

Qian Gao, Xukun Shen
2021 Sensors  
Experiments show that the framework achieved superior performance in both supervised and semi-supervised learning modes.  ...  At present, supervised learning methods have achieved impressive results, but, due to domain bias, the trained model cannot be directly applied to a new scene.  ...  Inter-Domain Semi-Supervised Learning The inter-domain semi-supervised learning mode was also designed for the circumstance of lack of labeled images.  ... 
doi:10.3390/s21072272 pmid:33804973 fatcat:mn62lg7wind63dfwk7kuwjggxe

Semi-Supervised Learning and Domain Adaptation in Natural Language Processing

Anders Søgaard
2013 Synthesis Lectures on Human Language Technologies  
The link between these two topics is that what is known of the test domain often comes in the form of an unlabeled sample, and hence semi-supervised techniques constitute an important class of adaptation  ...  To cope with data sparsity, a common strategy is semi-supervised learning, in which a small labeled data set is augmented by a larger amount of (typically more abundant) unlabeled data.  ...  The main topics of semi-supervised learning and adaptation are then presented in approximately equalsized portions, with adaptation split into two chapters covering techniques for known and unknown test  ... 
doi:10.2200/s00497ed1v01y201304hlt021 fatcat:4lldaytsozawbaejgdx3ikw4ie

Semi-supervised few-shot learning approach for plant diseases recognition

Yang Li, Xuewei Chao
2021 Plant Methods  
Methods In this paper, we proposed a semi-supervised few-shot learning approach to solve the plant leaf diseases recognition.  ...  In terms of selecting pseudo-labeled samples in the semi-supervised process, we adopted the confidence interval to determine the number of unlabeled samples for pseudo-labelling adaptively.  ...  Results of adaptive selection of pseudo-labeled samples As described in "Adaptive selection of pseudo-labeled samples" section, pseudo-labeled samples' adaptive selection is crucial for the proposed semi-supervised  ... 
doi:10.1186/s13007-021-00770-1 pmid:34176505 fatcat:2wxdfcn74reijionk7xznnmuxe

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

Qian Wang, Toby P. Breckon
2021 arXiv   pre-print
It is naturally suitable for supervised HDA but has also been extended for semi-supervised HDA where the unlabelled target domain samples are available.  ...  Heterogeneous Domain Adaptation (HDA) addresses the transfer learning problems where data from the source and target domains are of different modalities (e.g., texts and images) or feature dimensions (  ...  In this section, we describe the CDSPP algorithm which is naturally for supervised heterogeneous domain adaptation but can be used to address the semi-supervised heterogeneous domain adaptation problem  ... 
arXiv:2004.12427v3 fatcat:rx5dgopfjbhkxpf6eua3itxywy

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  ...  Specifically, SDASL conducts the learning by simultaneously minimizing the classification error, preserving the structure within and across domains, and restricting similarity defined on unlabeled target  ...  By consolidating the idea of semi-supervised learning and subspace learning for domain adaptation, this paper presents a novel Semi-supervised Domain Adaptation with Subspace Learning (SDASL) framework  ... 
doi:10.1109/cvpr.2015.7298826 dblp:conf/cvpr/YaoPNLM15 fatcat:uxgbcxd2kfagtj5nknmsmuo234
« Previous Showing results 1 — 15 out of 64,353 results