- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[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 - Classifying High Resolution Remote Sensing Images by Fine-Tuned VGG Deep Networks
摘要： Deep convolutional networks perform well in remote sensing (RS) image classification. Usually, it is difficult to obtain a large number of labeled samples in remote sensing classification tasks. Traditionally, the acquisition of remote sensing images is quite different from the photos provided by digital cameras. However, the imaging system for high resolution (HR) RS images (often with RGB 3 channels) is similar to those provided by digital cameras. In the paper, a transfer learning algorithm based on deep neural networks is proposed to attack the problem of lacking labeled RS samples, in particular on the context of pre-trained deep convolutional networks, i.e., VGGNet. Here, the VGGNet is trained on labeled multimedia images provided by 'ImageNet Large Scale Visual Recognition Challenge' (ILSVRC). In the proposed strategy, the VGGNet is adopted as a base classifier, and then labeled RS data samples are exploited to fine-tune higher hidden layers in the 16-layer VGG deep neural networks by the back-propagation algorithm. The proposed method is denoted as RS-VGGNet. The proposed RS-VGGNet is validated by real HR remote sensing images, which were acquired from the National Agriculture Imagery Program (NAIP) dataset. Experimental results show that the RS-VGGNet can achieve a higher accuracy compared to the original VGGNet and shallow machine learning methods. And the proposed RS-VGGNet significantly reduces training times and computing burden as well.
关键词： transfer learning,high resolution remote sensing image,Fine-tuning VGGNet,deep neural network
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 - Gan-Based Domain Adaptation for Object Classification
摘要： Recent trends in image classification focus on training deep neural networks that require having a large amount of training images related to the considered task. However, obtaining enough labeled image samples is often time-consuming and expensive. An alternative solution proposed is to transfer the knowledge learned while solving one problem to another but related problem, also called transfer learning. Domain adaptation is a type of transfer learning that deals with learning a model that performs well on two datasets that have different (but somehow correlated) data distributions. In this work, we present a new domain adaptation method based on generative adversarial networks (GANs) in the context of aerial image classification. Experimental results obtained on two datasets for a single object scenario show that the proposed method is particularly promising.
关键词： Deep learning,GAN,domain adaptation,transfer learning
更新于2025-09-09 09:28:46
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Transfer Learning from Synthetic to Real Images Using Variational Autoencoders for Precise Position Detection
摘要： Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not achieve the desired performance in the real world due to a gap between synthetic and real images. We propose a method that transfers learned detection of an object position from a simulation environment to the real world. This method uses only a significantly limited dataset of real images while leveraging a large dataset of synthetic images using variational autoencoders. Additionally, the proposed method consistently performed well in different lighting conditions, in the presence of other distractor objects, and on different backgrounds. Experimental results showed that it achieved accuracy of 1.5mm to 3.5mm on average. Furthermore, we showed how the method can be used in a real-world scenario like a “pick-and-place” robotic task.
关键词： variational autoencoder,transfer learning,position detection,deep learning,computer simulation
更新于2025-09-09 09:28:46
-
[IEEE 2018 7th International Conference on Computer and Communication Engineering (ICCCE) - Kuala Lumpur, Malaysia (2018.9.19-2018.9.20)] 2018 7th International Conference on Computer and Communication Engineering (ICCCE) - Finger Vein Identification Based On Transfer Learning of AlexNet
摘要： Nowadays finger vein-based validation systems are getting extra attraction among other authentication systems due to high security in terms of ensuring data confidentiality. This system works by recognizing patterns from finger vein images and these images are captured using a camera based on near-infrared technology. In this research, we focused finger vein identification system by using our own finger vein dataset, we trained it with transfer learning of AlexNet model and verified by test images. We have done three different experiments with the same dataset but different sizes of data. Therefore, we obtained varied predictability with 95% accuracy from the second experiment.
关键词： Biometric Identification,AlexNet,Finger vein,Transfer learning
更新于2025-09-09 09:28:46
-
A novel surface roughness measurement method based on the red and green aliasing effect
摘要： A common requirement in many machine learning algorithms is that the training data is sufficient. However, in the visual measurement of surface roughness, this requirement often can't be meet due to the reason that it is time-consuming and expensive to process and label the training samples. To address this issue, this paper proposes a novel method to establish an advanced roughness predictive model with less standard training samples based on inductive transfer learning. The experimental results show that the proposed method has superior measurement performance, and can maintain the average relative error of 12.57% even when the training data is insufficient. This indicates that the proposed method can provide a new strategy for improving the visual roughness measurement performance.
关键词： Roughness measurement,Index design,Inductive transfer learning,Machine vision
更新于2025-09-09 09:28:46
-
Development of an Automated Screening System for Retinopathy of Prematurity Using a Deep Neural Network for Wide-angle Retinal Images
摘要： Background: Retinopathy of prematurity (ROP) is one of the main causes of childhood blindness. However, insufficient ophthalmologists are qualified for ROP screening. Objective: To evaluate the performance of a deep neural network (DNN) for automated screening of ROP. Methods: The training and test sets came from 420,365 wide-angle retina images from ROP screening. A transfer learning scheme was designed to train the DNN classifier. First, a pre-processing classifier images. Then, pediatric ophthalmologists labeled each image as either ROP or negative. The labeled training set (8090 positive images and 9711 negative ones) was used to fine-tune three candidate DNN classifiers (AlexNet, VGG-16, and GoogLeNet) with the transfer learning approach. The resultant classifiers were evaluated on a test data set of 1742 samples, and compared with five independent pediatric retinal ophthalmologists. The ROC (receiver operating characteristic) curve, ROC area under the curve (AUC) and P-R (precision-recall) curve on the test data set were analyzed. Accuracy, precision, sensitivity (recall), specificity, F1 score, Youden index, and MCC (Matthews correlation coefficient) were evaluated at different sensitivity cutoffs. The data from the five pediatric ophthalmologists were plotted in the ROC and P-R curves to visualize their performances. Results: VGG-16 achieved the best performance. At the cutoff point that maximized F1 score in the precision-recall curve, the final DNN model achieved 98.8% accuracy, 94.1% sensitivity, 99.3% specificity, and 93.0% precision. This was comparable to the pediatric ophthalmologists (98.8% accuracy, 93.5% sensitivity, 99.5% specificity and 96.7% precision). Conclusion: In the screening of ROP using the evaluation of wide-angel retinal images, DNNs had high accuracy, sensitivity, specificity, and precision, comparable to that of pediatric ophthalmologists.
关键词： image classification,retinopathy of prematurity,transfer learning,deep neural network,wide-angle retinal image,computer-aided diagnosis
更新于2025-09-09 09:28:46
-
[IEEE ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, AB (2018.4.15-2018.4.20)] 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Classification of Corals in Reflectance and Fluorescence Images Using Convolutional Neural Network Representations
摘要： Coral species, with complex morphology and ambiguous boundaries, pose a great challenge for automated classification. CNN activations, which are extracted from fully connected layers of deep networks (FC features), have been successfully used as powerful universal representations in many visual tasks. In this paper, we investigate the transferability and combined performance of FC features and CONV features (extracted from convolutional layers) in the coral classification of two image modalities (reflectance and fluorescence), using a typical deep network (e.g. VGGNet). We exploit vector of locally aggregated descriptors (VLAD) encoding and principal component analysis (PCA) to compress dense CONV features into a compact representation. Experimental results demonstrate that encoded CONV3 features achieve superior performances on reflectance and fluorescence coral images, compared to FC features. The combination of these two features further improves the overall accuracy and achieves state-of-the-art performance on the challenging EFC dataset.
关键词： deep convolutional features,Transfer learning,coral image classification,VLAD encoding,fluorescence
更新于2025-09-09 09:28:46
-
CoinNet: Copy Initialization Network for Multispectral Imagery Semantic Segmentation
摘要： Remote sensing imagery semantic segmentation refers to assigning a label to every pixel. Recently, deep convolutional neural networks (CNNs)-based methods have presented an impressive performance in this task. Due to the lack of sufficient labeled remote sensing images, researchers usually utilized transfer learning (TL) strategies to fine tune networks which were pretrained in huge RGB-scene data sets. Unfortunately, this manner may not work if the target images are multispectral/hyperspectral. The basic assumption of TL is that the low-level features extracted by the former layers are similar in most data sets, hence users only require to train the parameters in the last layers that are specific to different tasks. However, if one should use a pretrained deep model imagery in RGB data for multispectral /hyperspectral semantic segmentation, the structure of the input layer has to be adjusted. In this case, the first convolutional layer has to be trained using the multispectral /hyperspectral data sets which are much smaller. Apparently, the feature representation ability of the first convolutional layer will decrease and it may further harm the following layers. In this letter, we propose a new deep learning model, COpy INitialization Network (CoinNet), for multispectral imagery semantic segmentation. The major advantage of CoinNet is that it can make full use of the initial parameters in the pretrained network’s first convolutional layer. Comparison experiments on a challenging multispectral data set have demonstrated the effectiveness of the proposed improvement. The demo and a trained network will be published in our homepage.
关键词： deep convolutional network,CoinNet,transfer learning (TL),semantic segmentation
更新于2025-09-09 09:28:46