Salman Khaleghian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Salman Khaleghian has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Andrea Marinoni
Department of Computer Science and Technology, University of Cambridge, Cambridge, U.K.
4 shared publications - Torbjorn Eltoft
Department of Physics and Technology, UiT The Arctic University of Norway, Troms, Norway
3 shared publications - Thomas Kræmer
Faculty of Science and Technology, University of Tromsø—The Arctic University of Norway, Tromsø, Norway
2 shared publications - Anders Andersen
UiT The Arctic University of Norway
1 shared publication Andreas Cziferszky
British Antarctic Survey, Cambridge, U.K.
1 shared publicationAndrew Fleming
British Antarctic Survey, Cambridge, U.K.
1 shared publication
Latest Publications
- Open Access
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 84569-84578
AFSD: Adaptive Feature Space Distillation for Distributed Deep Learning
We propose a novel and adaptive feature space distillation method (AFSD) to reduce the communication overhead among distributed computers. The proposed method improves the Codistillation process by supporting longer update interval rates. AFSD performs knowledge distillates across the models infrequently and provides flexibility to the models in terms of exploring diverse variations in the training process. We perform knowledge distillation in terms of sharing the feature space instead of output only. Therefore, we also propose a new loss function for the Codistillation technique in AFSD. Using the feature space leads to more efficient knowledge transfer between models with a longer update interval rates. In our method, the models can achieve the same accuracy as Allreduce and Codistillation with fewer epochs.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 84569-84578
Open AccessAFSD: Adaptive Feature Space Distillation for Distributed Deep Learning
We propose a novel and adaptive feature space distillation method (AFSD) to reduce the communication overhead among distributed computers. The proposed method improves the Codistillation process by supporting longer update interval rates. AFSD performs knowledge distillates across the models infrequently and provides flexibility to the models in terms of exploring diverse variations in the training process. We perform knowledge distillation in terms of sharing the feature space instead of output only. Therefore, we also propose a new loss function for the Codistillation technique in AFSD. Using the feature space leads to more efficient knowledge transfer between models with a longer update interval rates. In our method, the models can achieve the same accuracy as Allreduce and Codistillation with fewer epochs.
- Open Access
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 10761-10772
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification
In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples and a relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using a limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semisupervised reference methods.
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 10761-10772
Open AccessDeep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification
In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples and a relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using a limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semisupervised reference methods.
- Open Access
- 26 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 9038-9063
ExtremeEarth Meets Satellite Data From Space
Bringing together a number of cutting-edge technologies that range from storing extremely large volumes of data all the way to developing scalable machine learning and deep learning algorithms in a distributed manner and having them operate over the same infrastructure poses unprecedented challenges. One of these challenges is the integration of European Space Agency (ESA)'s Thematic Exploitation Platforms (TEPs) and data information access service platforms with a data platform, namely Hopsworks, which enables scalable data processing, machine learning, and deep learning on Copernicus data, and development of very large training datasets for deep learning architectures targeting the classification of Sentinel images. In this article, we present the software architecture of ExtremeEarth that aims at the development of scalable deep learning and geospatial analytics techniques for processing and analyzing petabytes of Copernicus data. The ExtremeEarth software infrastructure seamlessly integrates existing and novel software platforms and tools for storing, accessing, processing, analyzing, and visualizing large amounts of Copernicus data. New techniques in the areas of remote sensing and artificial intelligence with an emphasis on deep learning are developed. These techniques and corresponding software presented in this article are to be integrated with and used in two ESA TEPs, namely Polar and Food Security TEPs. Furthermore, we present the integration of Hopsworks with the Polar and Food Security use cases and the flow of events for the products offered through the TEPs.
- 26 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 9038-9063
Open AccessExtremeEarth Meets Satellite Data From Space
Bringing together a number of cutting-edge technologies that range from storing extremely large volumes of data all the way to developing scalable machine learning and deep learning algorithms in a distributed manner and having them operate over the same infrastructure poses unprecedented challenges. One of these challenges is the integration of European Space Agency (ESA)'s Thematic Exploitation Platforms (TEPs) and data information access service platforms with a data platform, namely Hopsworks, which enables scalable data processing, machine learning, and deep learning on Copernicus data, and development of very large training datasets for deep learning architectures targeting the classification of Sentinel images. In this article, we present the software architecture of ExtremeEarth that aims at the development of scalable deep learning and geospatial analytics techniques for processing and analyzing petabytes of Copernicus data. The ExtremeEarth software infrastructure seamlessly integrates existing and novel software platforms and tools for storing, accessing, processing, analyzing, and visualizing large amounts of Copernicus data. New techniques in the areas of remote sensing and artificial intelligence with an emphasis on deep learning are developed. These techniques and corresponding software presented in this article are to be integrated with and used in two ESA TEPs, namely Polar and Food Security TEPs. Furthermore, we present the integration of Hopsworks with the Polar and Food Security use cases and the flow of events for the products offered through the TEPs.
- Open Access
- 29 April 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (9) , 1734
Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks
We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results.
- 29 April 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (9) , 1734
Open AccessSea Ice Classification of SAR Imagery Based on Convolution Neural Networks
We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results.