- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2019 IEEE International Conference on Space Optical Systems and Applications (ICSOS) - Portland, OR, USA (2019.10.14-2019.10.16)] 2019 IEEE International Conference on Space Optical Systems and Applications (ICSOS) - Inter-Satellite Integrated Laser Communication/Ranging Link with Feedback-Homodyne Detection and Fractional Symbol Ranging
摘要： In real-life problems, the following semi-supervised domain adaptation scenario is often encountered: we have full access to some source data, which is usually very large; the target data distribution is under certain unknown transformation of the source data distribution; meanwhile, only a small fraction of the target instances come with labels. The goal is to learn a prediction model by incorporating information from the source domain that is able to generalize well on the target test instances. We consider an explicit form of transformation functions and especially linear transformations that maps examples from the source to the target domain, and we argue that by proper preprocessing of the data from both source and target domains, the feasible transformation functions can be characterized by a set of rotation matrices. This naturally leads to an optimization formulation under the special orthogonal group constraints. We present an iterative coordinate descent solver that is able to jointly learn the transformation as well as the model parameters, while the geodesic update ensures the manifold constraints are always satis?ed. Our framework is suf?ciently general to work with a variety of loss functions and prediction problems. Empirical evaluations on synthetic and real-world experiments demonstrate the competitive performance of our method with respect to the state-of-the-art.
关键词： transfer learning,semi-supervised learning,Domain adaptation
更新于2025-09-19 17:13:59
-
[IEEE 2019 44th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz) - Paris, France (2019.9.1-2019.9.6)] 2019 44th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz) - A Gap Waveguide Fed Circular Polarization Antenna in the Millimeter-Wave Range
摘要： Due to its wide applications in practice, face recognition has been an active research topic. With the availability of adequate training samples, many machine learning methods could yield high face recognition accuracy. However, under the circumstance of inadequate training samples, especially the extreme case of having only a single training sample, face recognition becomes challenging. How to deal with con?icting concerns of the small sample size and high dimensionality in one-sample face recognition is critical for its achievable recognition accuracy and feasibility in practice. Being different from the conventional methods for global face recognition based on generalization ability promotion and local face recognition depending on image segmentation, a single-sample face recognition algorithm based on locality preserving projection (LPP) feature transfer is proposed here. First, transfer sources are screened to obtain the selective sample source using the whitened cosine similarity metric. Second, we project the vectors of source faces and target faces into feature subspace by LPP, respectively, and calculate the feature transfer matrix to approximate the mapping relationship on source faces and target faces in subspace. Then, the feature transfer matrix is used on training samples to transfer the original macro characteristics to target macro characteristics. Finally, the nearest neighbor classi?er is used for face recognition. Our results based on popular databases FERET, ORL, and Yale demonstrate the superiority of the proposed LPP feature transfer-based one-sample face recognition algorithm when compared with popular single-sample face recognition algorithms, such as (PC)2A and Block FLDA.
关键词： one-sample,Feature extraction,face recognition,locality preserving projection,transfer learning
更新于2025-09-19 17:13:59
-
[IEEE 2019 International Joint Conference on Neural Networks (IJCNN) - Budapest, Hungary (2019.7.14-2019.7.19)] 2019 International Joint Conference on Neural Networks (IJCNN) - Transfer Learning Using Ensemble Neural Networks for Organic Solar Cell Screening
摘要： Organic Solar Cells are a promising technology for solving the clean energy crisis in the world. However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis. For a solar cell, the most important property is the power conversion efficiency which is dependent on the highest occupied molecular orbitals (HOMO) values of the donor molecules. Recently, machine learning techniques have proved to be very useful in building predictive models for HOMO values of donor structures of Organic Photovoltaic Cells (OPVs). Since experimental datasets are limited in size, current machine learning models are trained on data derived from calculations based on density functional theory (DFT). Molecular line notations such as SMILES or InChI are popular input representations for describing the molecular structure of donor molecules. The two types of line representations encode different information, such as SMILES defines the bond types while InChi defines protonation. In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential of transfer learning from a sizeable DFT-computed dataset- Harvard CEP to build more robust predictive models for relatively smaller HOPV datasets. Harvard CEP dataset contains molecular structures and properties for 2.3 million candidate donor structures for OPV while HOPV contains DFT-computed and experimental values of 350 and 243 molecules respectively. Our results demonstrate significant performance improvement from the use of transfer learning and leveraging both molecular representations.
关键词： Organic Solar Cells,InChI,SINet,HOMO values,SMILES,Transfer Learning,Machine Learning
更新于2025-09-16 10:30:52
-
[IEEE 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) - Amsterdam, Netherlands (2019.9.24-2019.9.26)] 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) - Knowledge Transfer via Convolution Neural Networks for Multi-Resolution Lawn Weed Classification
摘要： Weed identi?cation and classi?cation are essential and challenging tasks for site-speci?c weed control. Object-based image analysis making use of spatial information is adopted in this study for the weed classi?cation because the spectral similarity between the weeds and crop is high. With the availability of a wide range of sensors, it is likely to capture weed imagery at various altitudes and with different speci?cations of the sensor. In this paper, we propose a novel method using transfer learning to deal with multi-resolution images from various sensors via Convolutional Neural Networks (CNN). CNN trained for a typical image data set and the trained weights are transferred to other data sets of different resolutions. In this way, the new data sets can be classi?ed by ?ne-tuning the network using a small number of training samples, which reduces the need of big data to train the model. To avoid over-?tting during the ?ne-tuning, small deep learning architecture is proposed and investigated using the parameters of the initial layers of pre-trained model. The sizes of training samples are investigated for their impact on the performance of ?ne-tuning. Experiments were conducted with ?eld data, which show that the proposed method outperforms the direct training method in terms of recognition accuracy and computation cost.
关键词： Hyperspectral images,Resolution,Convolutional Neural Network (CNN),Weed Mapping,Transfer Learning
更新于2025-09-12 10:27:22
-
Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model for Hyperspectral Image Classification
摘要： Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning (TL) that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral–spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active TL is then exploited to transfer the pretrained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domains by the corresponding active learning (AL) strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel AL strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross data set and intraimage; and 3) the learned deep joint spectral–spatial feature representation is more generic and robust than many joint spectral–spatial feature representations. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular data sets.
关键词： multiple-feature representation,transfer learning (TL),hyperspectral image (HSI) classification,deep learning,Active learning (AL),stacked sparse autoencoder (SSAE)
更新于2025-09-10 09:29:36
-
Transfer Learning for Soil Spectroscopy Based on Convolutional Neural Networks and Its Application in Soil Clay Content Mapping Using Hyperspectral Imagery
摘要： Soil spectra are often measured in the laboratory, and there is an increasing number of large-scale soil spectral libraries establishing across the world. However, calibration models developed from soil libraries are difficult to apply to spectral data acquired from the field or space. Transfer learning has the potential to bridge the gap and make the calibration model transferrable from one sensor to another. The objective of this study is to explore the potential of transfer learning for soil spectroscopy and its performance on soil clay content estimation using hyperspectral data. First, a one-dimensional convolutional neural network (1D-CNN) is used on Land Use/Land Cover Area Frame Survey (LUCAS) mineral soils. To evaluate whether the pre-trained 1D-CNN model was transferrable, LUCAS organic soils were used to fine-tune and validate the model. The fine-tuned model achieved a good accuracy (coefficient of determination (R2) = 0.756, root-mean-square error (RMSE) = 7.07 and ratio of percent deviation (RPD) = 2.26) for the estimation of clay content. Spectral index, as suggested as a simple transferrable feature, was also explored on LUCAS data, but did not performed well on the estimation of clay content. Then, the pre-trained 1D-CNN model was further fine-tuned by field samples collect in the study area with spectra extracted from HyMap imagery, achieved an accuracy of R2 = 0.601, RMSE = 8.62 and RPD = 1.54. Finally, the soil clay map was generated with the fine-tuned 1D-CNN model and hyperspectral data.
关键词： hyperspectral imagery,soil spectroscopy,CNNs,deep learning,transfer learning
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES) - Las Palmas de Gran Canaria, Spain (2018.6.21-2018.6.23)] 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES) - Comparison of Different Deep-Learning Methods for Image Classification
摘要： In this paper, we showed how to solve exemplary image classification problem. The goal of image classification problem is to correctly classify the input image within the expected class/label. In our case, we focused on classifying the animal image into one of two categories: mammals or birds. That classification problem is not a trivial task using standard machine learning algorithms. The main reason for that is the fact that the algorithms are based on previously prepared features for classifying object. It is often done by hand by a researcher. Defining specific features for example how a beak looks, wing, tail, fur and etc. is natural for humans, but understanding it by computers is extremely difficult. However, nowadays deep learning algorithms managed to overcome some obstacles and work best for these types of problems. We can use Deep Neural Networks (DNN) in two ways - by developing it from scratch for the specific problem or using method calls transfer learning. The main goal of this paper is comparing the two methods by using them in a real-life example. We showed how to correctly prepare a dataset, create a DNN model from scratch and how to adjust it. We also showed how to use the transfer learning technique. All the steps we made are described in a way which allows for easy adaptation of these algorithms to similar problems.
关键词： deep learning,convolutional neural network,image classification,transfer learning
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom) - Ostrava, Czech Republic (2018.9.17-2018.9.20)] 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom) - Deep Learning Based Automated Extraction of Intra-Retinal Layers for Analyzing Retinal Abnormalities
摘要： Extraction of retinal layers from optical coherence tomography (OCT) scans is critical for analyzing retinal anomalies and manual segmentation of these retinal layers is a very cumbersome task. Recently, deep learning has gained much popularity in medical image analysis due to its underlying precision and robustness. Many researchers have utilized deep learning for extracting retinal layers from OCT images. However, to the best of our knowledge, there is no literature available that presents a robust segmentation framework that is able to extract retinal layers from OCT scans having different retinal pathological syndromes. Therefore, this paper presents a deep convolutional neural network and structure tensor-based segmentation framework (CNN-STSF) for the fully automated segmentation of up to eight retinal layers from normal as well as diseased OCT scans. First of all, the proposed framework computes coherent tensor from the candidate scan through which retinal layers are extracted. Afterwards, the pixels representing the layers are further classified using cloud based deep convolutional neural network (CNN) model trained on 1,200 retinal layers patches. CNN model in the proposed framework computes the probability of each layer pixels and assign it to be part of that layer for which it has the highest probability. The proposed framework was tested and validated on more than 39,000 retinal OCT scans from different publicly available datasets and from local Armed Forces Institute of Ophthalmology (AFIO) dataset where it outperformed all the existing solutions by achieving the overall layer segmentation accuracy of 0.9375.
关键词： Transfer learning,Convolutional neural network (CNN),Deep learning,AlexNet
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Convolutional Neural Networks for Cloud Screening: Transfer Learning from Landsat-8 to Proba-V
摘要： Cloud detection is a key issue for exploiting the information from Earth observation satellites multispectral sensors. For Proba-V, cloud detection is challenging due to the limited number of spectral bands. Advanced machine learning methods, such as convolutional neural networks (CNN), have shown to work well on this problem provided enough labeled data. However, simultaneous collocated information about the presence of clouds is usually not available or requires a great amount of manual labor. In this work, we propose to learn from the available Landsat-8 cloud masks datasets and transfer this learning to solve the Proba-V cloud detection problem. CNN are trained with Landsat images adapted to resemble Proba-V characteristics and tested on a large set of real Proba-V scenes. Developed models outperform current operational Proba-V cloud detection without being trained with any real Proba-V data. Moreover, cloud detection accuracy can be further increased if the CNN are fine-tuned using a limited amount of Proba-V data.
关键词： Proba-V,Transfer Learning,CNN,Cloud detection,Domain Adaptation,Landsat-8
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Transfer Learning with Convolutional Networks for Atmospheric Parameter Retrieval
摘要： The Infrared Atmospheric Sounding Interferometer (IASI) onboard the MetOp satellite series provides important measurements for Numerical Weather Prediction (NWP). Retrieving accurate atmospheric parameters from the raw data provided by IASI is a large challenge, but necessary in order to use the data in NWP models. Statistical models performance is compromised because of the extremely high spectral dimensionality and the high number of variables to be predicted simultaneously across the atmospheric column. All this poses a challenge for selecting and studying optimal models and processing schemes. Earlier work has shown non-linear models such as kernel methods and neural networks perform well on this task, but both schemes are computationally heavy on large quantities of data. Kernel methods do not scale well with the number of training data, and neural networks require setting critical hyperparameters. In this work we follow an alternative pathway: we study transfer learning in convolutional neural nets (CNNs) to alleviate the retraining cost by departing from proxy solutions (either features or networks) obtained from previously trained models for related variables. We show how features extracted from the IASI data by a CNN trained to predict a physical variable can be used as inputs to another statistical method designed to predict a different physical variable at low altitude. In addition, the learned parameters can be transferred to another CNN model and obtain results equivalent to those obtained when using a CNN trained from scratch requiring only fine tuning.
关键词： Infrared measurements,Convolutional Neural networks,parameter retrieval,Transfer Learning
更新于2025-09-10 09:29:36