2,374 Hits in 5.2 sec

Table of contents

2019 IEEE Transactions on Image Processing  
John, and P. L. Rosin 4606 Transfer Neural Trees: Semi-Supervised Heterogeneous Domain Adaptation and Beyond ................................ ................................................ W.-Y.  ...  Zheng 4671 Adaptive Transform Domain Image Super-Resolution via Orthogonally Regularized Deep Networks ................... ..............................................................................  ... 
doi:10.1109/tip.2019.2925750 fatcat:p6pnbp7tsrervmwma4oezunhpq

Domain Adaptation for Visual Applications: A Comprehensive Survey [article]

Gabriela Csurka
2017 arXiv   pre-print
The aim of this paper is to give an overview of domain adaptation and transfer learning with a specific view on visual applications.  ...  After a general motivation, we first position domain adaptation in the larger transfer learning problem.  ...  Concerning heterogeneous or multi-modal deep domain adaptation, we can mention the Transfer Neural Trees [156] proposed to relate heterogeneous cross-domain data.  ... 
arXiv:1702.05374v2 fatcat:5va4oz4evjfhxgxddflpbb6pxi

2020 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 30

2020 IEEE transactions on circuits and systems for video technology (Print)  
., TCSVT Jan. 2020 217-231 Hu, X., see Zhu, L., TCSVT Oct. 2020 3358-3371 Hu, Y., Lu, M., Xie, C., and Lu, X  ...  ., and Zeng, B., MUcast: Linear Uncoded Multiuser TCSVT Nov. 2020 4299-4308 Hu, R., see Chen, L., TCSVT Dec. 2020 4513-4525 Hu, R., see Wang, X., TCSVT Nov. 2020 4309-4320 Hu, X., see Zhang, X  ...  Li, Y., +, TCSVT Oct. 2020 3777-3787 Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch- Based Image Retrieval.  ... 
doi:10.1109/tcsvt.2020.3043861 fatcat:s6z4wzp45vfflphgfcxh6x7npu

Activity Recognition with Evolving Data Streams

Zahraa S. Abdallah, Mohamed Medhat Gaber, Bala Srinivasan, Shonali Krishnaswamy
2018 ACM Computing Surveys  
CCS Concepts: r General and reference → Surveys and overviews; r Theory of computation → Streaming models; Machine learning theory; r Computing methodologies → Transfer learning; r Hardware → Sensor applications  ...  The perspective of this paper is to review the adaptation capabilities of activity recognition techniques in streaming environment.  ...  That includes supervised, unsupervised, and semi-supervised learning. The second strand focuses on the dynamic capabilities of the recognition system beyond the learning phase.  ... 
doi:10.1145/3158645 fatcat:xsgcvmjy7rbifpfkmrclbhdwsa

Deep Visual Domain Adaptation: A Survey [article]

Mei Wang, Weihong Deng
2018 arXiv   pre-print
transferable representations by embedding domain adaptation in the pipeline of deep learning.  ...  Second, we summarize deep domain adaption approaches into several categories based on training loss, and analyze and compare briefly the state-of-the-art methods under these categories.  ...  An overview of different settings of domain adaptation 2) In the semi-supervised DA, both limited labeled data, One-step Domain adaptation Homogeneous Heterogeneous Supervised Semi-Supervised  ... 
arXiv:1802.03601v4 fatcat:d5hwwecipjfjzmh7725lmepzfe

Oblique view individual tree crown delineation

Christian Kempf, Jiaojiao Tian, Franz Kurz, Pablo D'Angelo, Thomas Schneider, Peter Reinartz
2021 International Journal of Applied Earth Observation and Geoinformation  
Individual tree crown (ITC) segmentation supports numerous applications in forest management and ecology.  ...  In the second step, the contour of the visible part of a candidate tree in images with known orientation is obtained by means of ray casting and concave hull calculation.  ...  Last, but not least, we would like to express our gratitude to Daniele Cerra, Maximillian Langenheinrich, Lukas Krieger and Xiangtian Yuan for proofreading the draft of this article.  ... 
doi:10.1016/j.jag.2021.102314 fatcat:qvatzp24rbg5rgnw3bqn332jqy

Machine Learning in Chemical Engineering : A Perspective

Artur M. Schweidtmann, Erik Esche, Asja Fischer, Marius Kloft, Jens-Uwe Repke, Sebastian Sager, Alexander Mitsos
2021 Chemie - Ingenieur - Technik (2021). doi:10.1002/cite.202100083  
representation, (4) heterogeneity of data, (5) safety and trust in ML applications, and (6) creativity.  ...  We identify six challenges that will open new methods for CE and formulate new types of problems for ML: (1) optimal decision making, (2) introducing and enforcing physics in ML, (3) information and knowledge  ...  MK acknowledges support by the Carl-Zeiss Foundation, by the German Research Foundation (DFG) award KL 2698/2-1, and by the Federal Ministry of Science and Education (BMBF) awards 01IS18051A and 031B0770E  ... 
doi:10.18154/rwth-2021-09826 fatcat:7tlvcx22urd27fpjfbw4iqhr7a

Transfer learning strategies for credit card fraud detection

Bertrand Lebichot, Theo Verhelst, Yann-Ael Le Borgne, Liyun He-Guelton, Frederic Oble, Gianluca Bontempi
2021 IEEE Access  
The authors and the parties cited above have no competing interests.  ...  We thank this agency for allowing us to conduct both fundamental and applied research. B. Lebichot also thanks LouRIM, Université Catholique de Louvain, Belgium for their support.  ...  This case is known as semi-supervised domain adaptation and it is one of the three most common configurations (see Table 1 inspired from [11] ).  ... 
doi:10.1109/access.2021.3104472 fatcat:gryi7nzwhjhgbemt3me6sm7of4

A survey on data‐efficient algorithms in big data era

Amina Adadi
2021 Journal of Big Data  
less training data and in particular less human supervision.  ...  by (iii) transferring knowledge from rich-data domains into poor-data domains, or by (iv) altering data-hungry algorithms to reduce their dependency upon the amount of samples, in a way they can perform  ...  The most prominent examples of this class of methods are: (i) semi-supervised support vector machine and (ii) semi-supervised neural networks.  ... 
doi:10.1186/s40537-021-00419-9 fatcat:v4uahsvhlzdldlxqf24bshmja4

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 2622-2637 Improving Dataset Volumes and Model Accuracy With Semi-Supervised Iterative Self-Learning. Dupre, R., +, TIP 2020 4337-4348 Latent Elastic-Net Transfer Learning.  ...  Spoorthi, G.E., +, TIP 2020 4862-4872 Real-Time Quality Assessment of Pediatric MRI via Semi-Supervised Deep Nonlocal Residual Neural Networks.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Learning for Biomedical Information Extraction: Methodological Review of Recent Advances [article]

Feifan Liu, Jinying Chen, Abhyuday Jagannatha, Hong Yu
2016 arXiv   pre-print
In addition, we dive into open information extraction and deep learning, two emerging and influential techniques and envision next generation of BioIE.  ...  Biomedical information extraction (BioIE) is important to many applications, including clinical decision support, integrative biology, and pharmacovigilance, and therefore it has been an active research  ...  Approaches include unsupervised, semi-supervised, and distant supervision.  ... 
arXiv:1606.07993v1 fatcat:7d5om7zxxzhoviiriasrfwg3xi

A remote sensing derived data set of 100 million individual tree crowns for the National Ecological Observatory Network

Ben G Weinstein, Sergio Marconi, Stephanie A Bohlman, Alina Zare, Aditya Singh, Sarah J Graves, Ethan P White
2021 eLife  
Each canopy tree crown is represented by a rectangular bounding box and includes information on the height, crown area, and spatial location of the tree.  ...  Information on individual trees is important for understanding forest ecosystems but obtaining individual-level data at broad scales is challenging due to the costs and logistics of data collection.  ...  Acknowledgements We would like to thank NEON staff and in particular Tristan Goulden and Courtney Meier for their assistance and support.  ... 
doi:10.7554/elife.62922 fatcat:v3ehiuc7ovf2rbexewzylaopzy

A Survey of Unsupervised Deep Domain Adaptation [article]

Garrett Wilson, Diane J. Cook
2020 arXiv   pre-print
As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but  ...  Many single-source and typically homogeneous unsupervised deep domain adaptation approaches have thus been developed, combining the powerful, hierarchical representations from deep learning with domain  ...  By handling heterogeneous feature spaces or various other levels of supervision (e.g., semi-supervised learning [203] or weakly-supervised learning [221] ), domain adaptation may bring performance gains  ... 
arXiv:1812.02849v3 fatcat:paefg5cywbe3tjsp6dffnwkvxy

Automatic Sleep Staging: Recent Development, Challenges, and Future Directions [article]

Huy Phan, Kaare Mikkelsen
2021 arXiv   pre-print
Sleep staging, a fundamental step in sleep practice, is a suitable task for this and will be the focus in this article.  ...  This review aims to give a shared view of the authors on the most recent state-of-the-art development in automatic sleep staging, the challenges that still need to be addressed, and the future directions  ...  In any case, a better solution is to exploit semi-supervised domain adaptation methods, that incorporate semi-supervised learning (SSL) [127] and domain adaptation [130] , to leverage both labelled  ... 
arXiv:2111.08446v1 fatcat:7bdcpqsgcvemxjqjuw5rnhzwni

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey [article]

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
2021 arXiv   pre-print
, domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research.  ...  We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning  ...  Semi-supervised domain adaptation based In BMVC British Machine Vision Conference (BMVC), on dual-level domain mixing for semantic segmentation.  ... 
arXiv:2112.03241v1 fatcat:uzlehddvuvfwzf4dfbjimja45e
« Previous Showing results 1 — 15 out of 2,374 results