scholarly journals A Novel Framework Based on Mask R-CNN and Histogram Thresholding for Scalable Segmentation of New and Old Rural Buildings

2021 ◽  
Vol 13 (6) ◽  
pp. 1070
Author(s):  
Ying Li ◽  
Weipan Xu ◽  
Haohui Chen ◽  
Junhao Jiang ◽  
Xun Li
Keyword(s):  
Rural Areas ◽  
Deep Neural Networks ◽  
Training Data ◽  
The Novel ◽  
Remote Sensing Images ◽  
Average Precision ◽  
Training Samples ◽  
Rural Buildings ◽  
Segmentation Task ◽  
Instance Segmentation

Mapping new and old buildings are of great significance for understanding socio-economic development in rural areas. In recent years, deep neural networks have achieved remarkable building segmentation results in high-resolution remote sensing images. However, the scarce training data and the varying geographical environments have posed challenges for scalable building segmentation. This study proposes a novel framework based on Mask R-CNN, named Histogram Thresholding Mask Region-Based Convolutional Neural Network (HTMask R-CNN), to extract new and old rural buildings even when the label is scarce. The framework adopts the result of single-object instance segmentation from the orthodox Mask R-CNN. Further, it classifies the rural buildings into new and old ones based on a dynamic grayscale threshold inferred from the result of a two-object instance segmentation task where training data is scarce. We found that the framework can extract more buildings and achieve a much higher mean Average Precision (mAP) than the orthodox Mask R-CNN model. We tested the novel framework’s performance with increasing training data and found that it converged even when the training samples were limited. This framework’s main contribution is to allow scalable segmentation by using significantly fewer training samples than traditional machine learning practices. That makes mapping China’s new and old rural buildings viable.

scholarly journals Learning with small amount of data on various task

2020 ◽  
Author(s):  
Stefanie
Keyword(s):  
Deep Neural Networks ◽  
Learning Strategy ◽  
Teaching Strategy ◽  
Training Sample ◽  
Learning To Teach ◽  
Training Data ◽  
Training Dataset ◽  
Small Data ◽  
Training Samples ◽  
Teacher Model

As a student, I am learning knowledge with the help of teachers and the teacher plays a crucial role in our life. A wonderful instructor is able to teach a student with appropriate teaching materials. Therefore, in this project, I explore a teaching strategy called learning to teach (L2T) in which a teacher model could provide high-quality training samples to a student model. However, one major problem of L2T is that the teacher model will only select a subset of the training dataset as the final training data for the student. Learning to teach small-data learning strategy (L2TSDL) is proposed to solve this problem. In this strategy, the teacher model will calculate the importance score for every training sample and help students to make use of all training samples. To demonstrate the advantage of the proposed approach over L2T, I take the training of different deep neural networks (DNN) on image classification task as an exampleand show that L2TSDL could achieve good performance on both large and small dataset.

scholarly journals Instance Segmentation of Microscopic Foraminifera

2021 ◽  
Author(s):  
Thomas Haugland Johansen ◽  
Steffen Aagaard Sørensen ◽  
Kajsa Møllersen ◽  
Fred Godtliebsen
Keyword(s):  
Counting Process ◽  
Detection Task ◽  
Fine Tuning ◽  
Average Precision ◽  
Novel Object ◽  
Proposed Model ◽  
Model Weight ◽  
Segmentation Task ◽  
Future Work ◽  
Instance Segmentation

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

scholarly journals HaS-Net: A Heal and Select Mechanism to Securely Train DNNs against Backdoor Attacks

2021 ◽  
Author(s):  
Hassan Ali ◽  
Surya Nepal ◽  
Salil S. Kanhere ◽  
Sanjay K. Jha
Keyword(s):  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Training Data ◽  
Network Architectures ◽  
Success Rates ◽  
Defense Strategies ◽  
Consumer Complaint ◽  
Training Samples ◽  
Novel Variant

<div>We have witnessed the continuing arms race between backdoor attacks and the corresponding defense strategies on Deep Neural Networks (DNNs). However, most state-of-the-art defenses rely on the statistical sanitization of <i>inputs</i> or <i>latent DNN representations</i> to capture trojan behavior. In this paper, we first challenge the robustness of many recently reported defenses by introducing a novel variant of the targeted backdoor attack, called <i>low-confidence backdoor attack</i>. <i>Low-confidence attack</i> inserts the backdoor by assigning uniformly distributed probabilistic labels to the poisoned training samples, and is applicable to many practical scenarios such as Federated Learning and model-reuse cases. We evaluate our attack against five state-of-the-art defense methods, viz., STRIP, Gradient-Shaping, Februus, ULP-defense and ABS-defense, under the same threat model as assumed by the respective defenses and achieve Attack Success Rates (ASRs) of 99\%, 63.73%, 91.2%, 80% and 100%, respectively. After carefully studying the properties of the state-of-the-art attacks, including low-confidence attacks, we present <i>HaS-Net</i>, a mechanism to securely train DNNs against a number of backdoor attacks under the data-collection scenario. For this purpose, we use a reasonably small healing dataset, approximately 2% to 15% the size of training data, to heal the network at each iteration. We evaluate our defense for different datasets---Fashion-MNIST, CIFAR-10, Celebrity Face, Consumer Complaint and Urban Sound---and network architectures---MLPs, 2D-CNNs, 1D-CNNs---and against several attack configurations---standard backdoor attacks, invisible backdoor attacks, label-consistent attack and all-trojan backdoor attack, including their low-confidence variants. Our experiments show that <i>HaS-Nets</i> can decrease ASRs from over 90% to less than 15%, independent of the dataset, attack configuration and network architecture.</div>

scholarly journals Instance Segmentation of Microscopic Foraminifera

2021 ◽  
Vol 11 (14) ◽  
pp. 6543
Author(s):  
Thomas Haugland Johansen ◽  
Steffen Aagaard Sørensen ◽  
Kajsa Møllersen ◽  
Fred Godtliebsen
Keyword(s):  
Counting Process ◽  
Detection Task ◽  
Fine Tuning ◽  
Average Precision ◽  
Novel Object ◽  
Proposed Model ◽  
Model Weight ◽  
Segmentation Task ◽  
Future Work ◽  
Instance Segmentation

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78 on the classification and detection task, and 0.80 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84 and 0.86, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

scholarly journals HaS-Net: A Heal and Select Mechanism to Securely Train DNNs against Backdoor Attacks

2021 ◽  
Author(s):  
Hassan Ali ◽  
Surya Nepal ◽  
Salil S. Kanhere ◽  
Sanjay K. Jha
Keyword(s):  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Training Data ◽  
Network Architectures ◽  
Success Rates ◽  
Defense Strategies ◽  
Consumer Complaint ◽  
Training Samples ◽  
Novel Variant

<div>We have witnessed the continuing arms race between backdoor attacks and the corresponding defense strategies on Deep Neural Networks (DNNs). However, most state-of-the-art defenses rely on the statistical sanitization of <i>inputs</i> or <i>latent DNN representations</i> to capture trojan behavior. In this paper, we first challenge the robustness of many recently reported defenses by introducing a novel variant of the targeted backdoor attack, called <i>low-confidence backdoor attack</i>. <i>Low-confidence attack</i> inserts the backdoor by assigning uniformly distributed probabilistic labels to the poisoned training samples, and is applicable to many practical scenarios such as Federated Learning and model-reuse cases. We evaluate our attack against five state-of-the-art defense methods, viz., STRIP, Gradient-Shaping, Februus, ULP-defense and ABS-defense, under the same threat model as assumed by the respective defenses and achieve Attack Success Rates (ASRs) of 99\%, 63.73%, 91.2%, 80% and 100%, respectively. After carefully studying the properties of the state-of-the-art attacks, including low-confidence attacks, we present <i>HaS-Net</i>, a mechanism to securely train DNNs against a number of backdoor attacks under the data-collection scenario. For this purpose, we use a reasonably small healing dataset, approximately 2% to 15% the size of training data, to heal the network at each iteration. We evaluate our defense for different datasets---Fashion-MNIST, CIFAR-10, Celebrity Face, Consumer Complaint and Urban Sound---and network architectures---MLPs, 2D-CNNs, 1D-CNNs---and against several attack configurations---standard backdoor attacks, invisible backdoor attacks, label-consistent attack and all-trojan backdoor attack, including their low-confidence variants. Our experiments show that <i>HaS-Nets</i> can decrease ASRs from over 90% to less than 15%, independent of the dataset, attack configuration and network architecture.</div>

scholarly journals Detecting OpenStreetMap missing buildings by transferring pre-trained deep neural networks

2021 ◽  
Vol 2 ◽  
pp. 1-7
Author(s):  
Jan Pisl ◽  
Hao Li ◽  
Sven Lautenbach ◽  
Benjamin Herfort ◽  
Alexander Zipf
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Training Data ◽  
Fine Tuning ◽  
Target Area ◽  
Building Detection ◽  
Detection Model ◽  
Training Samples ◽  
Training Examples ◽  
Limited Training Samples

Abstract. Accurate and complete geographic data of human settlements is crucial for effective emergency response, humanitarian aid and sustainable development. Open- StreetMap (OSM) can serve as a valuable source of this data. As there are still many areas missing in OSM, deep neural networks have been trained to detect such areas from satellite imagery. However, in regions where little or no training data is available, training networks is problematic. In this study, we proposed a method of transferring a building detection model, which was previously trained in an area wellmapped in OSM, to remote data-scarce areas. The transferring was achieved via fine-tuning the model on limited training samples from the original training area and the target area. We validated the method by transferring deep neural networks trained in Tanzania to a site in Cameroon with straight distance of over 2600 km, and tested multiple variants of the proposed method. Finally, we applied the fine-tuned model to detect 1192 buildings missing OSM in a selected area in Cameroon. The results showed that the proposed method led to a significant improvement in f1-score with as little as 30 training examples from the target area. This is a crucial quality of the proposed method as it allows to fine-tune models to regions where OSM data is scarce.

Role of General Adversarial Networks in Mammogram Analysis: A Review

2020 ◽  
Vol 16 (7) ◽  
pp. 863-877
Author(s):  
Annapoorani Gopal ◽  
Lathaselvi Gandhimaruthian ◽  
Javid Ali
Keyword(s):  
Breast Tumor ◽  
Deep Neural Networks ◽  
Training Data ◽  
Learning Technology ◽  
Breast Cancers ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Tumor Extraction

The Deep Neural Networks have gained prominence in the biomedical domain, becoming the most commonly used networks after machine learning technology. Mammograms can be used to detect breast cancers with high precision with the help of Convolutional Neural Network (CNN) which is deep learning technology. An exhaustive labeled data is required to train the CNN from scratch. This can be overcome by deploying Generative Adversarial Network (GAN) which comparatively needs lesser training data during a mammogram screening. In the proposed study, the application of GANs in estimating breast density, high-resolution mammogram synthesis for clustered microcalcification analysis, effective segmentation of breast tumor, analysis of the shape of breast tumor, extraction of features and augmentation of the image during mammogram classification have been extensively reviewed.

scholarly journals Siamese Reconstruction Network: Accurate Image Reconstruction from Human Brain Activity by Learning to Compare

2019 ◽  
Vol 9 (22) ◽  
pp. 4749
Author(s):  
Lingyun Jiang ◽  
Kai Qiao ◽  
Linyuan Wang ◽  
Chi Zhang ◽  
Jian Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Human Brain ◽  
Brain Activity ◽  
Feature Space ◽  
Training Data ◽  
Reconstruction Method ◽  
Learning Method ◽  
Training Samples ◽  
Visual Reconstruction ◽  
Relationship Of

Decoding human brain activities, especially reconstructing human visual stimuli via functional magnetic resonance imaging (fMRI), has gained increasing attention in recent years. However, the high dimensionality and small quantity of fMRI data impose restrictions on satisfactory reconstruction, especially for the reconstruction method with deep learning requiring huge amounts of labelled samples. When compared with the deep learning method, humans can recognize a new image because our human visual system is naturally capable of extracting features from any object and comparing them. Inspired by this visual mechanism, we introduced the mechanism of comparison into deep learning method to realize better visual reconstruction by making full use of each sample and the relationship of the sample pair by learning to compare. In this way, we proposed a Siamese reconstruction network (SRN) method. By using the SRN, we improved upon the satisfying results on two fMRI recording datasets, providing 72.5% accuracy on the digit dataset and 44.6% accuracy on the character dataset. Essentially, this manner can increase the training data about from n samples to 2n sample pairs, which takes full advantage of the limited quantity of training samples. The SRN learns to converge sample pairs of the same class or disperse sample pairs of different class in feature space.

scholarly journals Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1713
Author(s):  
Songwei Gu ◽  
Rui Zhang ◽  
Hongxia Luo ◽  
Mengyao Li ◽  
Huamei Feng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Real Life ◽  
Attention Mechanism ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Natural Image ◽  
Remote Sensing Images ◽  
Training Time ◽  
Adversarial Networks ◽  
Remote Sensing Image Classification

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

scholarly journals An Improved Segmentation Method for Automatic Mapping of Cone Karst from Remote Sensing Data Based on DeepLab V3+ Model

2021 ◽  
Vol 13 (3) ◽  
pp. 441
Author(s):  
Han Fu ◽  
Bihong Fu ◽  
Pilong Shi
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Guizhou Province ◽  
Training Dataset ◽  
Optical Remote Sensing ◽  
Remote Sensing Images ◽  
Karst Landscape ◽  
Heritage Site ◽  
Training Samples ◽  
Input Module

The South China Karst, a United Nations Educational, Scientific and Cultural Organization (UNESCO) natural heritage site, is one of the world’s most spectacular examples of humid tropical to subtropical karst landscapes. The Libo cone karst in the southern Guizhou Province is considered as the world reference site for these types of karst, forming a distinctive and beautiful landscape. Geomorphic information and spatial distribution of cone karst is essential for conservation and management for Libo heritage site. In this study, a deep learning (DL) method based on DeepLab V3+ network was proposed to document the cone karst landscape in Libo by multi-source data, including optical remote sensing images and digital elevation model (DEM) data. The training samples were generated by using Landsat remote sensing images and their combination with satellite derived DEM data. Each group of training dataset contains 898 samples. The input module of DeepLab V3+ network was improved to accept four-channel input data, i.e., combination of Landsat RGB images and DEM data. Our results suggest that the mean intersection over union (MIoU) using the four-channel data as training samples by a new DL-based pixel-level image segmentation approach is the highest, which can reach 95.5%. The proposed method can accomplish automatic extraction of cone karst landscape by self-learning of deep neural network, and therefore it can also provide a powerful and automatic tool for documenting other type of geological landscapes worldwide.

Sign in / Sign up

Export Citation Format

Share Document