Filters








16,740 Hits in 3.4 sec

Special issue on "visual semantic analysis with weak supervision"

Luming Zhang, Yang Yang, Rongrong Ji, Roger Zimmermann
2017 Multimedia Systems  
Finally, we would like to thank all the authors who have contributed to this special issue. Thanks to all the people who help us to make this special issue a successful one.  ...  1 National University of Singapore, Singapore, Singapore Acknowledgments We also thank the reviewers for their efforts to guarantee the high quality of this special issue.  ...  This special issue will target the most recent technical progresses on learning techniques for visual semantic understanding with weak supervision, such as weakly labeled representative views.  ... 
doi:10.1007/s00530-016-0527-4 fatcat:72hcjiiwfzbk7mdrsumuia7rzy

Foreword: special issue for the journal track of the 9th Asian Conference on Machine Learning (ACML 2017)

Wee Sun Lee, Robert J. Durrant
2017 Machine Learning  
Unlike typical semi-supervised learning method, the proposed method does not depend on strong distributional assumptions.  ...  The paper "Semi-Supervised AUC Optimization based on Positive-Unlabeled Learning", by Tomoya Sakai, Gang Niu, and Masashi Sugiyama provides a semi-supervised learning method for maximizing the area under  ... 
doi:10.1007/s10994-017-5691-z fatcat:wzshsay22jbsxnqfq2wqjj66ka

Special Issue on Deep Learning in Biological Image and Signal Processing

2020 IEEE Signal Processing Magazine  
analysis • Unsupervised and weakly-supervised deep learning • Deep learning strategies in imaging genetics • Graph neural networks for connectivity analysis • Privacy-preserving distributed deep learning  ...  Fostering crosspollination between data-driven and model-driven approaches, the Special Issue aims to inspire researchers in developing novel solutions to current challenges of deep learning in biological  ...  analysis • Unsupervised and weakly-supervised deep learning • Deep learning strategies in imaging genetics • Graph neural networks for connectivity analysis • Privacy-preserving distributed deep learning  ... 
doi:10.1109/msp.2020.3028720 fatcat:an3exd7lmjadrhv75kzc4ds6vm

Special Issue on Deep Learning in Biological Image and Signal Processing

2021 IEEE Signal Processing Magazine  
analysis • Unsupervised and weakly supervised deep learning • Deep learning strategies in imaging genetics • Graph neural networks for connectivity analysis • Privacy-preserving distributed deep learning  ...  This special issue of IEEE Signal Processing Magazine provides a venue for a wide and diverse audience to survey recent research advances in deep learning for applications in biological image and signal  ...  analysis • Unsupervised and weakly supervised deep learning • Deep learning strategies in imaging genetics • Graph neural networks for connectivity analysis • Privacy-preserving distributed deep learning  ... 
doi:10.1109/msp.2020.3040489 fatcat:qys3d64ajncqpbyq2bl4lnoofm

Preface to the Special Issue on Robust Machine Learning for Open Scenarios

Enhong Chen, School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China, Yufeng Li, Quan Zou
2022 International Journal of Software and Informatics  
Specifically, this special issue encompasses machine learning for the cases of distribution changes, weakly supervised learning, model reuse, representation learning, reinforcement learning, adversarial  ...  We hope that this special issue will boost the research on robust machine learning in open scenarios in China.  ...  Confidence-weighted Learning for Feature Evolution put forward a confidence-weighted learning algorithm for feature evolution based on second-order information to address the replacement and disappearance  ... 
doi:10.21655/ijsi.1673-7288.00265 fatcat:lvhc2wd5nba7dfwq7vhx6ftvbu

Non-iterative approaches in training feed-forward neural networks and their applications

Xizhao Wang, Weipeng Cao
2018 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
Focusing on non-iterative approaches in training feed-forward neural networks, this special issue includes 12 papers to share the latest progress, current challenges, and potential applications of this  ...  This editorial presents a background of the special issue and a brief introduction to the 12 contributions.  ...  Antonio Di Nola, the Editor-in-Chief of Soft Computing, for his support to edit this special issue.  ... 
doi:10.1007/s00500-018-3203-0 fatcat:snmmbo3ys5a2plmpsyxowzye6a

Weakly Supervised Object Localization and Detection: A Survey [article]

Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang
2021 arXiv   pre-print
In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets  ...  As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems  ...  Robust Learning Theory To address the learning under uncertainty issue that is inherently existed in the weakly supervised learning process, robust learning strategy will become one of the key techniques  ... 
arXiv:2104.07918v1 fatcat:dwl6sjfzibdilnvjnrbifp4uke

Guest Editorial Annotation-Efficient Deep Learning: The Holy Grail of Medical Imaging

Nima Tajbakhsh, Holger Roth, Demetri Terzopoulos, Jianming Liang
2021 IEEE Transactions on Medical Imaging  
Overview of the topics covered in this Special Issue on annotationefficient deep learning. Fig. 2 . 2 Fig. 2.  ...  The Special Issue offers only four articles on this topic, leaving it under-investigated.  ... 
doi:10.1109/tmi.2021.3089292 pmid:34795461 pmcid:PMC8594751 fatcat:t7kufjbdyfgazng3gcuyuhawxu

Guided Learning Convolution System for DCASE 2019 Task 4 [article]

Liwei Lin, Xiangdong Wang, Hong Liu, Yueliang Qian
2019 arXiv   pre-print
To take advantage of the unlabeled data, we adopt Guided Learning for semi-supervised learning.  ...  We also analyze the effect of the synthetic data on the performance of the model and finally achieve an event-based F-measure of 45.43% on the validation set and an event-based F-measure of 42.7% on the  ...  its effects on weakly-supervised learning and unsupervised learning model and finally achieve an event-based F-measure of 45.43% on separately.  ... 
arXiv:1909.06178v1 fatcat:zuoodch5rrgt7ls73hzyihp32u

KDETM at NTCIR-12 Temporalia Task: Combining a Rule-based Classifier with Weakly Supervised Learning for Temporal Intent Disambiguation

Abu Nowshed Chy, Md Zia Ullah, Md Shajalal, Masaki Aono
2016 NTCIR Conference on Evaluation of Information Access Technologies  
applied to train the weakly supervised classifier.  ...  In our approach, we combine a rule-based classifier with weakly supervised classifier.  ...  We submitted three runs based on a rule-based classifier and two different machine learning classifiers (Naive-Bayes and SVM).  ... 
dblp:conf/ntcir/ChyUSA16 fatcat:cxhs4kv25nglvl2nvy76swwb2a

Special Issue on Generating Realistic Visual Data of Human Behavior

Xavier Alameda-Pineda, Elisa Ricci, Albert Ali Salah, Nicu Sebe, Shuicheng Yan
2020 International Journal of Computer Vision  
The second set of four papers in the special issue deal with generating faces.  ...  The special issue was preceded by the 9th International Workshop on Human Behavior Understanding, held at ECCV (September 2018 in Munich), organized by the guest editors with the focus theme of the special  ... 
doi:10.1007/s11263-020-01319-w fatcat:jky5wzgw4bbc3aluxnjq5vy6nm

Machine Learning Methods with Noisy, Incomplete or Small Datasets

Cesar F. Caiafa, Zhe Sun, Toshihisa Tanaka, Pere Marti-Puig, Jordi Solé-Casals
2021 Applied Sciences  
In this article, we present a collection of fifteen novel contributions on machine learning methods with low-quality or imperfect datasets, which were accepted for publication in the special issue "Machine  ...  We believe that this special issue will bring new ideas for solving this challenging problem, and will provide clear examples of application in real-world scenarios.  ...  The algorithm considers learning from strongly and weakly labeled data. On the other side, in [10] , Gil et al.  ... 
doi:10.3390/app11094132 doaj:b756026d4f1b45e89f158fe4378f7e8c fatcat:zpqxuxf5ora2xk3zpmge73tyl4

WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization [article]

Md Tahmid Rahman Laskar, Enamul Hoque, Jimmy Xiangji Huang
2020 arXiv   pre-print
To overcome this issue, in this paper, we propose a novel weakly supervised learning approach via utilizing distant supervision.  ...  Then, we iteratively train our summarization model on each single-document to alleviate the computational complexity issue that occurs while training neural summarization models in multiple documents (  ...  From now on, we denote ROUGE as R. (-4.24%) 41.01 (-4.27%) No, based on paired t-test (p ≤ .05) without Weakly Supervised Learning 40.01 (-6 .37%) 40.12 (-6.35%) Yes, based on paired t-test (p  ... 
arXiv:2011.01421v1 fatcat:fth4hcqwonafpcdptgrp3kwm6e

Webly Supervised Learning Meets Zero-shot Learning: A Hybrid Approach for Fine-Grained Classification

Li Niu, Ashok Veeraraghavan, Ashu Sabharwal
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
For the second direction, the performance gap between ZSL and traditional supervised learning is still very large.  ...  Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed framework.  ...  In this way, we can learn a more robust dictionary D t on the weakly-supervised categories.  ... 
doi:10.1109/cvpr.2018.00749 dblp:conf/cvpr/0002VS18 fatcat:cbm5njx6e5bd3h5oijexnzyhqm

KnowMAN: Weakly Supervised Multinomial Adversarial Networks [article]

Luisa März, Ehsaneddin Asgari, Fabienne Braune, Franziska Zimmermann, Benjamin Roth
2021 arXiv   pre-print
KnowMAN strongly improves results compared to direct weakly supervised learning with a pre-trained transformer language model and a feature-based baseline.  ...  This process of weakly supervised training may result in an over-reliance on the signals captured by the labeling functions and hinder models to exploit other signals or to generalize well.  ...  Acknowledgements This research was funded by the WWTF through theproject "Knowledge-infused Deep Learning for Nat-ural Language Processing" (WWTF Vienna ResearchGroup VRG19-008), by the Deutsche Forschungs-gemeinschaft  ... 
arXiv:2109.07994v1 fatcat:2t4ijbiihvghbjaeriqbaqcpqe
« Previous Showing results 1 — 15 out of 16,740 results