14,726 Hits in 4.6 sec

Deep Domain Adaptation under Deep Label Scarcity [article]

Amar Prakash Azad, Dinesh Garg, Priyanka Agrawal, Arun Kumar
2018 arXiv   pre-print
The goal behind Domain Adaptation (DA) is to leverage the labeled examples from a source domain so as to infer an accurate model in a target domain where labels are not available or in scarce at the best  ...  This approach requires a large number of labeled examples from the source domain to be able to infer a good model for the target domain.  ...  The field of domain adaptation (DA) aims at easing out learner's job under such stress situations by allowing a transfer of learned models to other domain that faces label scarcity or absence.  ... 
arXiv:1809.08097v1 fatcat:hqdy6xfdojfgxpe5mj6r2v3s7m

MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels [chapter]

Ziyuan Zhao, Kaixin Xu, Shumeng Li, Zeng Zeng, Cuntai Guan
2021 Lecture Notes in Computer Science  
Although deep unsupervised domain adaptation (UDA) can leverage well-established source domain annotations and abundant target domain data to facilitate cross-modality image segmentation and also mitigate  ...  We evaluate our method on MM-WHS 2017 dataset and demonstrate that our approach outperforms the state-of-the-art methods by a large margin under the source-label scarcity scenario.  ...  beneath D s s to improve the segmentation performance on D s under label scarcity.  ... 
doi:10.1007/978-3-030-87193-2_28 fatcat:cmqrhlvgpvba5kape4qawz5eti

Research on fault diagnosis method of deep transfer learning driven by simulation data

Zicheng Xiong, Mengwei Li, Yaohong Tang, Shungen Xiao, Mengmeng Song
2022 Vibroengineering PROCEDIA  
Sufficient labeled fault samples are the key to ensuring the performance of deep learning diagnostic models.  ...  The deep learning diagnosis model trained directly with simulation data lacks versatility and cannot be applied to fault diagnosis of real data.  ...  [11] proposed a deep transfer learning method based on sub-domain adaptation, by introducing sub-domain adaptation and adversarial learning, while aligning the local and global feature distributions  ... 
doi:10.21595/vp.2022.22674 fatcat:ama6rxd445gyhb4fqhen6dhev4

Dual-Component Deep Domain Adaptation: A New Approach for Cross Project Software Vulnerability Detection [chapter]

Van Nguyen, Trung Le, Olivier de Vel, Paul Montague, John Grundy, Dinh Phung
2020 Lecture Notes in Computer Science  
One possible solution is to employ deep domain adaptation (DA) which has recently witnessed enormous success in transferring learning from structural labeled to unlabeled data sources.  ...  Our aim in this paper is to propose Dual Generator-Discriminator Deep Code Domain Adaptation Network (Dual-GD-DDAN) for tackling the problem of transfer learning from labeled to unlabeled software projects  ...  This research was supported under the Defence Science and Technology Group's Next Generation Technologies Program.  ... 
doi:10.1007/978-3-030-47426-3_54 fatcat:ibdlwish7bcqnkefisvt3kkbo4

Optimization of Rural Smart Tourism Service Model with Internet of Things

Xiaoqing Hu, Muhammad Arif
2022 Security and Communication Networks  
When it comes to training, however, there exist source domain data sets that are completely labeled and can be used as a supplement to the target domain training data sets. (2) A personalized recommendation  ...  The main research contents of the paper are as follows: (1) A new algorithm for recommending tourism destinations with domain adaptability has been suggested.  ...  To put it another way, domain adaptation can address the issue of using labeled samples from the source domain data set to help classify data from the target domain when the distribution of data between  ... 
doi:10.1155/2022/6004728 fatcat:dzcdkoqjlbbrbk2t3gigsxnjgu

Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios [chapter]

Xiong Zhou, Saurabh Prasad
2020 Advances in Computer Vision and Pattern Recognition  
Challenges include limited ground truth (annotation is expensive and extensive labeling is often not feasible), and high dimensional nature of the data (each pixel is represented by hundreds of spectral  ...  In recent years, there has been an emergence of deep learning algorithms being applied to hyperspectral and multispectral imagery for remote sensing and biomedicine tasks.  ...  Transfer learning and Domain Adaptation Effective training has always been a challenge with deep learning models.  ... 
doi:10.1007/978-3-030-38617-7_5 fatcat:23ibk4ojbvepbpikxgjxan4i6e

Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity [article]

Nanqing Dong, Jiayi Wang, Irina Voiculescu
2022 arXiv   pre-print
The empirical results also provide insights into future research directions on partially supervised learning under data scarcity.  ...  This paper offers an empirical understanding of an under-explored problem, namely partially supervised multi-label classification (PSMLC), where a multi-label classifier is trained with only partially  ...  This is the first study of partially supervised multilabel classification (PSMLC) under data scarcity in the medical domain. 2.  ... 
arXiv:2204.08954v1 fatcat:63qpvfrhuzctjp23ova6zm4e4y

Transfer Adaptation Learning: A Decade Survey [article]

Lei Zhang, Xinbo Gao
2020 arXiv   pre-print
Broader solutions of transfer adaptation learning being created by researchers are identified, i.e., instance re-weighting adaptation, feature adaptation, classifier adaptation, deep network adaptation  ...  A research problem is characterized as transfer adaptation learning (TAL) when it needs knowledge correspondence between different moments/domains.  ...  ACKNOWLEDGMENT The author would like to thank the pioneer researchers in transfer learning, domain adaptation and other related fields. The author would also like to thank Dr. Mingsheng Long and Dr.  ... 
arXiv:1903.04687v2 fatcat:wurprqieffalnnp6isfkhh5y5i

Neural Unsupervised Domain Adaptation in NLP—A Survey [article]

Alan Ramponi, Barbara Plank
2020 arXiv   pre-print
Motivated by the latest advances, in this survey we review neural unsupervised domain adaptation techniques which do not require labeled target domain data.  ...  In contrast, learning from unlabeled data, especially under domain shift, remains a challenge.  ...  For many target applications, labeled data is lacking (Y scarcity), and even for pre-training general models data might be scarce (X scarcity).  ... 
arXiv:2006.00632v2 fatcat:n4g3yelofzdqpoacta3agjahde

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling [article]

Gaode Chen, Yijun Su, Xinghua Zhang, Anmin Hu, Guochun Chen, Siyuan Feng, Ji Xiang, Junbo Zhang, Yu Zheng
2022 arXiv   pre-print
., data missing and label scarcity) caused by inadequate services and infrastructures or imbalanced development levels of cities have seriously affected the urban computing tasks in real scenarios.  ...  With our adaptation of federated training and homomorphic encryption settings, CcFTL can effectively deal with the data privacy problem among cities.  ...  : We further explore the effectiveness of our model CcFTL under varying proportions of label scarcity in the target city.  ... 
arXiv:2206.00007v3 fatcat:kcuqefmq2zbyrifij6sknonapi

Meta learning to classify intent and slot labels with noisy few shot examples [article]

Shang-Wen Li, Jason Krone, Shuyan Dong, Yi Zhang, Yaser Al-onaizan
2020 arXiv   pre-print
Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU).  ...  We establish the task by defining few-shot splits on three public IC/SL datasets, ATIS, SNIPS, and TOP, and adding two types of natural noises (adaptation example missing/replacing and modality mismatch  ...  Transfer learning usually refers to pre-training initial models using mismatched domains with rich human annotations and then adapting the models with limited labels in targeted domains.  ... 
arXiv:2012.07516v1 fatcat:hrsgnmpf4fevvh2kdefvircymi

A Real Use Case of Semi-Supervised Learning for Mammogram Classification in a Local Clinic of Costa Rica [article]

Saul Calderon-Ramirez, Diego Murillo-Hernandez, Kevin Rojas-Salazar, David Elizondo, Shengxiang Yang, Miguel Molina-Cabello
2021 arXiv   pre-print
The scarcity of labeled data can also bring a challenge towards the application of transfer learning with models trained using these source datasets.  ...  It is shown that the use of semi-supervised deep learning combined with fine-tuning can provide a meaningful advantage when using scarce labeled observations.  ...  This work is partially supported by by the Ministry of Science, Innovation and Universities of Spain under grant number RTI2018-094645-B-  ... 
arXiv:2107.11696v1 fatcat:6jajcqzggreyxogav4sh7q6uym

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
Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly-labeled target domain.  ...  Notably, our approach is suitable for both homogeneous and heterogeneous domain adaptation by learning domain-specific projections.  ...  INTRODUCTION T HE scarcity principle 1 is one of the commonsense principles in our daily life. In the field of machine learning, the scarcity shows up in labeled samples.  ... 
arXiv:1906.07441v1 fatcat:2ontem74c5cvlo2qditieesx2u

Mining Label Distribution Drift in Unsupervised Domain Adaptation [article]

Peizhao Li, Zhengming Ding, Hongfu Liu
2020 arXiv   pre-print
Numerical results and empirical model analysis show that LMDAN delivers superior performance compared to other state-of-the-art domain adaptation methods under such scenarios.  ...  Finally, different from general domain adaptation experiments, we modify domain adaptation datasets to create the considerable label distribution drift between source and target domain.  ...  Among these settings, unsupervised domain adaptation, containing no label but only samples in target domain, is a challenging but practical one, owing to actual scenes are suffering from label-scarcity  ... 
arXiv:2006.09565v1 fatcat:pkpzkxeiijhqfas3h23zjh5rcy

Sparsely-Labeled Source Assisted Domain Adaptation [article]

Wei Wang, Zhihui Wang, Yuankai Xiang, Jing Sun, Haojie Li, Fuming Sun, Zhengming Ding
2020 arXiv   pre-print
This paper proposes a novel Sparsely-Labeled Source Assisted Domain Adaptation (SLSA-DA) algorithm to address the challenge with limited labeled source domain samples.  ...  Domain Adaptation (DA) aims to generalize the classifier learned from the source domain to the target domain.  ...  Label quality and its sufficiency are both important in context of domain adaptation (DA), especially for deep learning DA frameworks [7] .  ... 
arXiv:2005.04111v1 fatcat:hka66nryzjd6pdatrsev6fleam
« Previous Showing results 1 — 15 out of 14,726 results