- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) - Vancouver, BC, Canada (2018.8.29-2018.8.31)] 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) - Deep Transfer Learning for Hyperspectral Image Classification
摘要： Hyperspectral image (HSI) includes a vast quantities of samples, large number of bands, as well as randomly occurring redundancy. Classifying such complex data is challenging, and the classification performance generally is affected significantly by the amount of labeled training samples. Collecting such labeled training samples is labor and time consuming, motivating the idea of borrowing and reusing labeled samples from other pre-existing related images. Therefore transfer learning, which can mitigate the semantic gap between existing and new HSI, has recently drawn increasing research attention. However, existing transfer learning methods for HSI which concentrated on how to overcome the divergence among images, may neglect the high level latent features during the transfer learning process. In this paper, we present two novel ideas based on this observation. We propose constructing and connecting higher level features for the source and target HSI data, to further overcome the cross-domain disparity. Different from existing methods, no priori knowledge on the target domain is needed for the proposed classification framework, and the proposed framework works for both homogeneous and heterogenous HSI data. Experimental results on real world hyperspectral images indicate the significance of the proposed method in HSI classification.
关键词： supervised classification,salient samples,Hyperspectral image,Transfer learning
更新于2025-09-23 15:23:52
-
Fully automated detection of retinal disorders by image-based deep learning
摘要： Purpose With the aging population and the global diabetes epidemic, the prevalence of age-related macular degeneration (AMD) and diabetic macular edema (DME) diseases which are the leading causes of blindness is further increasing. Intravitreal injections with anti-vascular endothelial growth factor (anti-VEGF) medications are the standard of care for their indications. Optical coherence tomography (OCT), as a noninvasive imaging modality, plays a major part in guiding the administration of anti-VEGF therapy by providing detailed cross-sectional scans of the retina pathology. Fully automating OCT image detection can significantly decrease the tedious clinician labor and obtain a faithful pre-diagnosis from the analysis of the structural elements of the retina. Thereby, we explore the use of deep transfer learning method based on the visual geometry group 16 (VGG-16) network for classifying AMD and DME in OCT images accurately and automatically. Method A total of 207,130 retinal OCT images between 2013 and 2017 were selected from retrospective cohorts of 5319 adult patients from the Shiley Eye Institute of the University of California San Diego, the California Retinal Research Foundation, Medical Center Ophthalmology Associates, the Shanghai First People’s Hospital, and the Beijing Tongren Eye Center, with 109,312 images (37,456 with choroidal neovascularization, 11,599 with diabetic macular edema, 8867 with drusen, and 51,390 normal) for the experiment. After images preprocessing, 1000 images (250 images from each category) from 633 patients were selected as validation dataset while the rest images from another 4686 patients were used as training dataset. We used deep transfer learning method to fine-tune the VGG-16 network pre-trained on the ImageNet dataset, and evaluated its performance on the validation dataset. Then, prediction accuracy, sensitivity, specificity, and receiver-operating characteristic (ROC) were calculated. Results Experimental results proved that the proposed approach had manifested superior performance in retinal OCT images detection, which achieved a prediction accuracy of 98.6%, with a sensitivity of 97.8%, a specificity of 99.4%, and introduced an area under the ROC curve of 100%. Conclusion Deep transfer learning method based on the VGG-16 network shows significant effectiveness on classification of retinal OCT images with a relatively small dataset, which can provide assistant support for medical decision-making. Moreover, the performance of the proposed approach is comparable to that of human experts with significant clinical experience. Thereby, it will find promising applications in an automatic diagnosis and classification of common retinal diseases.
关键词： Diabetic macular edema,Visual geometry group 16 network,Age-related macular degeneration,Optical coherence tomography,Deep transfer learning
更新于2025-09-23 15:22:29
-
Deep-learning based surface region selection for deep inspiration breath hold (DIBH) monitoring in left breast cancer radiotherapy
摘要： Deep inspiration breath hold (DIBH) with surface supervising is a common technique for cardiac dose reduction in left breast cancer radiotherapy. Surface supervision accuracy relies on the characteristics of surface region. In this study, a convolutional neural network (CNN) based automatic region-of-interest (ROI) selection method was proposed to select an optimal surface ROI for DIBH surface monitoring. The curvature entropy and the normal of each vertex on the breast cancer patient surface were calculated and formed as representative maps for ROI selection learning. 900 ROIs were randomly extracted from each patient’s surface representative map, and the corresponding rigid ROI registration errors (RE) were calculated. The VGG-16 (a 16-layer network structure developed by Visual Geometry Group(VGG) from University of Oxford) pre-trained on a large natural image database ImageNet were fine-tuned using 27 thousand extracted ROIs and the corresponding RE from thirty patients. The RE prediction accuracy of the trained model was validated on additional ten patients. Satisfactory RE predictive accuracies were achieved with the root mean square error (RMSE)/mean absolute error (MAE) smaller than 1mm/0.7mm in translations and 0.45°/0.35° in rotations, respectively. The REs of the model selected ROIs on ten testing cases is close to the minimal predicted RE with mean RE differences <1mm and <0.5° for translation and rotation, respectively. The proposed RE predictive model can be utilized for selecting a quasi-optimal ROI in left breast cancer DIBH radiotherapy (DIBH-RT).
关键词： DIBH,ROI selection,transfer learning,motion monitoring
更新于2025-09-23 15:21:21
-
[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 - Time-Scale Transferring Deep Convolutional Neural Network for Mapping Early Rice
摘要： In recent years, the use of deep learning in remote sensing domain has made it possible to automate mapping in large-scale. In this paper, we propose a transfer learning method which pre-train a convolutional neural network (CNN) with middle-resolution remote sensing data in 2016, and fine-tune it in following years with a spot of high-resolution remote sensing data in 2017. We used the fine-tuned model to mapping the early-rice in 25 countries which cost only 21 minutes, and yielded an overall accuracy of 81.68%. The result demonstrate that the convolutional neural network model can transfer in different time period with little adjustment in a very high accuracy.
关键词： middle-resolution data,convolutional neural network,time-scale,transfer learning
更新于2025-09-23 15:21:21
-
[Advances in Intelligent Systems and Computing] Recent Findings in Intelligent Computing Techniques Volume 709 (Proceedings of the 5th ICACNI 2017, Volume 3) || Optimal Approach for Image Recognition Using Deep Convolutional Architecture
摘要： In the recent time, deep learning has achieved huge popularity due to its performance in various machine learning algorithms. Deep learning as hierarchical or structured learning attempts to model high-level abstractions in data by using a group of processing layers. The foundation of deep learning architectures is inspired by the understanding of information processing and neural responses in human brain. The architectures are created by stacking multiple linear or nonlinear operations. The article mainly focuses on the state-of-the-art deep learning models and various real-world application-speci?c training methods. Selecting optimal architecture for speci?c problem is a challenging task; at a closing stage of the article, we proposed optimal approach to deep convolutional architecture for the application of image recognition.
关键词： Deep neural networks,Image recognition,Image processing,Transfer learning,Convolutional neural networks,Deep learning
更新于2025-09-23 15:21:01
-
[IEEE 2020 IEEE International Conference on Big Data and Smart Computing (BigComp) - Busan, Korea (South) (2020.2.19-2020.2.22)] 2020 IEEE International Conference on Big Data and Smart Computing (BigComp) - Transfer Learning for Photovoltaic Power Forecasting with Long Short-Term Memory Neural Network
摘要： Data-driven modeling is one of the research hotspots of photovoltaic (PV) power prediction. However, for some newly built PV power plants, there are not enough historical data to train an accurate model. Therefore, constructing a forecasting model for the PV plants lacking historical data is an urgent problem to be solved. In this paper, we propose a method to transfer the knowledge obtained from historical solar irradiance data to the output prediction. Firstly, the based on hyperparameters of the long short-term memory neural network (LSTM) are optimized and the weights in the neurons are pre-trained, then fine-tuning the deep transfer model with PV output data. In this way, knowledge can be transferred to PV output data. The from solar experimental results show that the proposed method can significantly reduce the prediction error.
关键词： Long short-term memory,Transfer learning,Photovoltaic power forecasting,Hyperparameter optimization,Data mining
更新于2025-09-23 15:21:01
-
Deep transfer learning-based hologram classification for molecular diagnostics
摘要： Lens-free digital in-line holography (LDIH) is a promising microscopic tool that overcomes several drawbacks (e.g., limited field of view) of traditional lens-based microcopy. However, extensive computation is required to reconstruct object images from the complex diffraction patterns produced by LDIH. This limits LDIH utility for point-of-care applications, particularly in resource limited settings. We describe a deep transfer learning (DTL) based approach to process LDIH images in the context of cellular analyses. Specifically, we captured holograms of cells labeled with molecular-specific microbeads and trained neural networks to classify these holograms without reconstruction. Using raw holograms as input, the trained networks were able to classify individual cells according to the number of cell-bound microbeads. The DTL-based approach including a VGG19 pretrained network showed robust performance with experimental data. Combined with the developed DTL approach, LDIH could be realized as a low-cost, portable tool for point-of-care diagnostics.
关键词： LDIH,VGG19,hologram classification,molecular diagnostics,deep transfer learning
更新于2025-09-23 15:21:01
-
Method for Mapping Rice Fields in Complex Landscape Areas Based on Pre-Trained Convolutional Neural Network from HJ-1 A/B Data
摘要： Accurate and timely information about rice planting areas is essential for crop yield estimation, global climate change and agricultural resource management. In this study, we present a novel pixel-level classi?cation approach that uses convolutional neural network (CNN) model to extract the features of enhanced vegetation index (EVI) time series curve for classi?cation. The goal is to explore the practicability of deep learning techniques for rice recognition in complex landscape regions, where rice is easily confused with the surroundings, by using mid-resolution remote sensing images. A transfer learning strategy is utilized to ?ne tune a pre-trained CNN model and obtain the temporal features of the EVI curve. Support vector machine (SVM), a traditional machine learning approach, is also implemented in the experiment. Finally, we evaluate the accuracy of the two models. Results show that our model performs better than SVM, with the overall accuracies being 93.60% and 91.05%, respectively. Therefore, this technique is appropriate for estimating rice planting areas in southern China on the basis of a pre-trained CNN model by using time series data. And more opportunity and potential can be found for crop classi?cation by remote sensing and deep learning technique in the future study.
关键词： mapping rice ?elds,convolutional neural network,time series of vegetation index,complex landscape,transfer learning
更新于2025-09-23 15:21:01
-
[IEEE 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT) - Bangalore, India (2018.5.18-2018.5.19)] 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT) - Solar Photovoltaic Powered Smart Garbage Monitoring System Using GSM/GPS
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2025-09-23 15:19:57
-
[IEEE 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Xi'an, China (2018.11.7-2018.11.10)] 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA) - Image Classification Method in DR Image Based on Transfer Learning
摘要： Until now many cancer cases have been discovered in their early stages based on Computer Aided Diagnosis (CAD) system. There are many methods in the medical image processing field have been proposed to address this issue, and the result of these methods was deficient. Further, the application of AI in DR images is not widespread in hospitals. The classification process in the DR image is more difficult than other types of images. In this paper, we use transfer learning which is based on Inception V3 model to classify the DR images. We used the weight of Inception V3 model which was trained in the ImageNet dataset, and fine-tuning in our own dataset. Comparing to other proposed methods, our result had a higher accuracy.
关键词： DR images,Transfer Learning,medical image,CAD
更新于2025-09-19 17:15:36