A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
SAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning
2019
IEEE Access
To address domain shift and task transfer problems caused by differences between simulated and real data, we propose a model that integrates meta-learning and adversarial domain adaptation. ...
INDEX TERMS Synthetic aperture radar (SAR), target recognition, convolutional neural network (CNN), meta-learning, adversarial domain adaptation. ...
By introducing meta-learning and domain adaptation into the application scenario of transfer learning, our model addresses the cross-domain and cross-task transfer problem. ...
doi:10.1109/access.2019.2948618
fatcat:3mql7wr6nzgnfhxvhgvmdipium
Zero-Resource Cross-Domain Named Entity Recognition
[article]
2020
arXiv
pre-print
Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains. ...
We first introduce a Multi-Task Learning (MTL) by adding a new objective function to detect whether tokens are named entities or not. ...
Acknowledgments This work is partially funded by ITF/319/16FP and MRP/055/18 of the Innovation Technology Commission, the Hong Kong SAR Government. ...
arXiv:2002.05923v2
fatcat:waj3ssskzbgidl74uowht3jroq
Meta-Transfer Learning for Code-Switched Speech Recognition
[article]
2020
arXiv
pre-print
We therefore propose a new learning method, meta-transfer learning, to transfer learn on a code-switched speech recognition system in a low-resource setting by judiciously extracting information from high-resource ...
Based on experimental results, our model outperforms existing baselines on speech recognition and language modeling tasks, and is faster to converge. ...
Acknowledgments This work has been partially funded by ITF/319/16FP and MRP/055/18 of the Innovation Technology Commission, the Hong Kong SAR Government, and School of Engineering Ph.D. ...
arXiv:2004.14228v1
fatcat:4uvz2sdztjdzpd5soddpwkmfsu
A Global Model Approach to Robust Few-Shot SAR Automatic Target Recognition
[article]
2023
arXiv
pre-print
Unlike competing approaches which require a pristine labeled dataset for pretraining via meta-learning, our approach learns highly transferable features from unlabeled data that have little-to-no relation ...
In real-world scenarios, it may not always be possible to collect hundreds of labeled samples per class for training deep learning-based SAR Automatic Target Recognition (ATR) models. ...
SSL has shown great promise for transfer and few-shot learning in the natural imagery domain [5] , but has not been studied widely in the context of SAR ATR. ...
arXiv:2303.10800v1
fatcat:4bbd6zl4fbfz5c5h6dsvcxysg4
Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition
2019
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
We evaluate the proposed embedding method on the code-switching English-Spanish Named Entity Recognition dataset in a multilingual and cross-lingual setting. ...
In this paper, we propose Multilingual Meta-Embeddings (MME), an effective method to learn multilingual representations by leveraging monolingual pre-trained embeddings. ...
This work has been partially funded by ITF/319/16FP and MRP/055/18 of the Innovation Technology Commission, the Hong Kong SAR Government, and School of Engineering Ph.D. ...
doi:10.18653/v1/w19-4320
dblp:conf/rep4nlp/WinataLF19
fatcat:2dzci5vdxnejjdrqmzdcb2s76i
SAR Target Recognition via Meta-Learning and Amortized Variational Inference
2020
Sensors
To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). ...
The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. ...
Feature extraction can also be carried out in the transformation domain, where the images are and cross-task SAR-ATR problems. ...
doi:10.3390/s20205966
pmid:33096933
fatcat:clkcauglbfeurnvnblxnkzfuni
Domain Adaptive Few-Shot Learning for ISAR Aircraft Recognition with Transferred Attention and Weighting Importance
2023
Electronics
Few-shot learning provides a new approach to solving the above problem by transferring useful knowledge from other domains, such as optical images from satellites. ...
Nevertheless, it fails to fully consider the domain shift between the source and target domains, generally neglecting the transferability of training samples in the learning process. ...
Acknowledgments: All authors would sincerely thank the reviewers and editors for their suggestions and opinions for improving this article. ...
doi:10.3390/electronics12132909
fatcat:fy7fqe4qfreqjbtdffluhortw4
Meta-Learning for Few-Shot Land Cover Classification
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
We evaluate the modelagnostic meta-learning (MAML) algorithm on classification and segmentation tasks using globally and regionally distributed datasets. ...
We find that few-shot model adaptation outperforms pre-training with regular gradient descent and fine-tuning on the (1) Sen12MS dataset and (2) DeepGlobe dataset when the source domain and target domain ...
In the setting where p(X, y) are identical in the source domain and target domain, a model trained on the source domain transfers perfectly to the target domain. ...
doi:10.1109/cvprw50498.2020.00108
dblp:conf/cvpr/RusswurmW0L20
fatcat:tiqxnwuhgnfdzow6ufgm2dwfcm
Synthetic Aperture Radar Automatic Target Recognition Based on a Simple Attention Mechanism
2023
International Journal of Interactive Multimedia and Artificial Intelligence
A simple but effective channel attention module is proposed for Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). ...
With the Attentionbased model and the One Policy Learning Rate-based architecture, we were able to obtain recognition rate of 100% and 99.8%, respectively. ...
99.54% Xinyan et al. [57] 2019 SAR Image Target Recognition with CNN CNN 99.18% Dong et al. [58] 2019 Target Recognition in SAR Images Via Dimension Reduction in The Frequency Domain Bandwidth Modeling ...
doi:10.9781/ijimai.2023.02.004
fatcat:q2cnmkyrbzfpxft2bz7kffpcbe
A Review of Data Augmentation Methods of Remote Sensing Image Target Recognition
2023
Remote Sensing
been made in the accuracy of image target recognition through the use of deep learning. ...
In the research of remote sensing image target recognition based on deep learning, an insufficient number of research samples is often an encountered issue; too small a number of research samples will ...
Transfer learning is a machine learning method that transfers knowledge from one domain (source domain) to another domain (target domain) so that the target domain can achieve better learning effects. ...
doi:10.3390/rs15030827
fatcat:ikdosxfy3zgsvplf54nm2o2otu
Few-Shot High-Resolution Range Profile Ship Target Recognition Based on Task-Specific Meta-Learning with Mixed Training and Meta Embedding
2023
Remote Sensing
Firstly, a Task-Adaptive Mixed Transfer (TAMT) strategy is proposed, which combines basic learning with meta-learning, to reduce the likelihood of overfitting and enhance adaptability for recognizing new ...
Secondly, a Prototype Network is introduced to enable the recognition of new classes of targets with limited samples. ...
Conclusions In this study, a novel few-shot HRRP target recognition approach, denoted as Task-Specific Mate-learning, is introduced to address the challenge posed by limited labeled samples and high target ...
doi:10.3390/rs15225301
fatcat:vygg5enjdvbpbj47owlx4x5ixq
Azimuth-Aware Discriminative Representation Learning for Semi-Supervised Few-Shot SAR Vehicle Recognition
2023
Remote Sensing
Among the current methods of synthetic aperture radar (SAR) automatic target recognition (ATR), unlabeled measured data and labeled simulated data are widely used to elevate the performance of SAR ATR. ...
The phase data and amplitude data of SAR targets are all taken into consideration in this article. ...
Few-Shot Learning and Its Applications in SAR Target Recognition (1). ...
doi:10.3390/rs15020331
fatcat:vechxu43qfblneehx6v6xpygpu
A Survey on Open-Set Image Recognition
[article]
2023
arXiv
pre-print
Then, we compare the performances of some typical and state-of-the-art OSR methods on both coarse-grained datasets and fine-grained datasets under both standard-dataset setting and cross-dataset setting ...
Open-set image recognition (OSR) aims to both classify known-class samples and identify unknown-class samples in the testing set, which supports robust classifiers in many realistic applications, such ...
[118, 119] firstly formally defined the open-set long-tailed recognition task, and handled it based on a dynamic meta-embedding mechanism. ...
arXiv:2312.15571v1
fatcat:6kddlq4jxfbgvpisnj7mbrbfgu
Interactive Design of Object Classifiers in Remote Sensing
2014
2014 22nd International Conference on Pattern Recognition
We propose an approach for on-line learning of such detectors using user interactions. ...
We show that our model and algorithms outperform several state-of-the-art baselines for feature extraction and learning in remote sensing. ...
ACKNOWLEDGMENT The authors would like to thank DigitalGlobe, Astrium Services, and USGS for providing TerraSAR-X images used in this study, and the IEEE GRSS Data Fusion Technical Committee for organizing ...
doi:10.1109/icpr.2014.444
dblp:conf/icpr/Saux14
fatcat:runq43ou4nb6pnilejmqdkf35a
A Class Imbalance Loss for Imbalanced Object Recognition
2020
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In addition, the Mixed National Institute of Standards and Technology dataset and the Moving and Stationary Target Acquisition and Recognition dataset are sampled to imbalance datasets to verify the effectiveness ...
mean average precision than focal loss and cross-entropy loss. ...
Imbalanced Few-Shot Learning Few-shot classification is a well-established problem in the domain of supervised recognition tasks, where the goal is to learn a classifier to recognize unseen classes when ...
doi:10.1109/jstars.2020.2995703
fatcat:rrxhxnllz5epxhblbrtysjrwu4
« Previous
Showing results 1 — 15 out of 1,575 results