Paper Group ANR 889
Outlining where humans live – The World Settlement Footprint 2015. Generalizable prediction of academic performance from short texts on social media. GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier. Assessment of central serous chorioretinopathy (CSC) depicted on color fundus photographs using deep Learning. Correlat …
Outlining where humans live – The World Settlement Footprint 2015
| Title | Outlining where humans live – The World Settlement Footprint 2015 |
| Authors | Mattia Marconcini, Annekatrin Metz-Marconcini, Soner Üreyen, Daniela Palacios-Lopez, Wiebke Hanke, Felix Bachofer, Julian Zeidler, Thomas Esch, Noel Gorelick, Ashwin Kakarla, Emanuele Strano |
| Abstract | Human settlements are the cause and consequence of most environmental and societal changes on Earth; however, their location and extent is still under debate. We provide here a new 10m resolution (0.32 arc sec) global map of human settlements on Earth for the year 2015, namely the World Settlement Footprint 2015 (WSF2015). The raster dataset has been generated by means of an advanced classification system which, for the first time, jointly exploits open-and-free optical and radar satellite imagery. The WSF2015 has been validated against 900,000 samples labelled by crowdsourcing photointerpretation of very high resolution Google Earth imagery and outperforms all other similar existing layers; in particular, it considerably improves the detection of very small settlements in rural regions and better outlines scattered suburban areas. The dataset can be used at any scale of observation in support to all applications requiring detailed and accurate information on human presence (e.g., socioeconomic development, population distribution, risks assessment, etc.). |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12707v1 |
| https://arxiv.org/pdf/1910.12707v1.pdf | |
| PWC | https://paperswithcode.com/paper/outlining-where-humans-live-the-world |
| Repo | |
| Framework | |
Generalizable prediction of academic performance from short texts on social media
| Title | Generalizable prediction of academic performance from short texts on social media |
| Authors | Ivan Smirnov |
| Abstract | It has already been established that digital traces can be used to predict various human attributes. In most cases, however, predictive models rely on features that are specific to a particular source of digital trace data. In contrast, short texts written by users $-$ tweets, posts, or comments $-$ are ubiquitous across multiple platforms. In this paper, we explore the predictive power of short texts with respect to the academic performance of their authors. We use data from a representative panel of Russian students that includes information about their educational outcomes and activity on a popular networking site, VK. We build a model to predict academic performance from users’ posts on VK and then apply it to a different context. In particular, we show that the model could reproduce rankings of schools and universities from the posts of their students on social media. We also find that the same model could predict academic performance from tweets as well as from VK posts. The generalizability of a model trained on a relatively small data set could be explained by the use of continuous word representations trained on a much larger corpus of social media posts. This also allows for greater interpretability of model predictions. |
| Tasks | |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.00463v1 |
| https://arxiv.org/pdf/1912.00463v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalizable-prediction-of-academic |
| Repo | |
| Framework | |
GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier
| Title | GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier |
| Authors | Guanxiong Liu, Issa Khalil, Abdallah Khreishah |
| Abstract | Machine learning models, especially neural network (NN) classifiers, are widely used in many applications including natural language processing, computer vision and cybersecurity. They provide high accuracy under the assumption of attack-free scenarios. However, this assumption has been defied by the introduction of adversarial examples – carefully perturbed samples of input that are usually misclassified. Many researchers have tried to develop a defense against adversarial examples; however, we are still far from achieving that goal. In this paper, we design a Generative Adversarial Net (GAN) based adversarial training defense, dubbed GanDef, which utilizes a competition game to regulate the feature selection during the training. We analytically show that GanDef can train a classifier so it can defend against adversarial examples. Through extensive evaluation on different white-box adversarial examples, the classifier trained by GanDef shows the same level of test accuracy as those trained by state-of-the-art adversarial training defenses. More importantly, GanDef-Comb, a variant of GanDef, could utilize the discriminator to achieve a dynamic trade-off between correctly classifying original and adversarial examples. As a result, it achieves the highest overall test accuracy when the ratio of adversarial examples exceeds 41.7%. |
| Tasks | Feature Selection |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02585v1 |
| http://arxiv.org/pdf/1903.02585v1.pdf | |
| PWC | https://paperswithcode.com/paper/gandef-a-gan-based-adversarial-training |
| Repo | |
| Framework | |
Assessment of central serous chorioretinopathy (CSC) depicted on color fundus photographs using deep Learning
| Title | Assessment of central serous chorioretinopathy (CSC) depicted on color fundus photographs using deep Learning |
| Authors | Yi Zhen, Hang Chen, Xu Zhang, Meng Liu, Xin Meng, Jian Zhang, Jiantao Pu |
| Abstract | To investigate whether and to what extent central serous chorioretinopathy (CSC) depicted on color fundus photographs can be assessed using deep learning technology. We collected a total of 2,504 fundus images acquired on different subjects. We verified the CSC status of these images using their corresponding optical coherence tomography (OCT) images. A total of 1,329 images depicted CSC. These images were preprocessed and normalized. This resulting dataset was randomly split into three parts in the ratio of 8:1:1 respectively for training, validation, and testing purposes. We used the deep learning architecture termed InceptionV3 to train the classifier. We performed nonparametric receiver operating characteristic (ROC) analyses to assess the capability of the developed algorithm to identify CSC. The Kappa coefficient between the two raters was 0.48 (p < 0.001), while the Kappa coefficients between the computer and the two raters were 0.59 (p < 0.001) and 0.33 (p < 0.05).Our experiments showed that the computer algorithm based on deep learning can assess CSC depicted on color fundus photographs in a relatively reliable and consistent way. |
| Tasks | |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.04540v1 |
| http://arxiv.org/pdf/1901.04540v1.pdf | |
| PWC | https://paperswithcode.com/paper/assessment-of-central-serous |
| Repo | |
| Framework | |
Correlation via synthesis: end-to-end nodule image generation and radiogenomic map learning based on generative adversarial network
| Title | Correlation via synthesis: end-to-end nodule image generation and radiogenomic map learning based on generative adversarial network |
| Authors | Ziyue Xu, Xiaosong Wang, Hoo-Chang Shin, Dong Yang, Holger Roth, Fausto Milletari, Ling Zhang, Daguang Xu |
| Abstract | Radiogenomic map linking image features and gene expression profiles is useful for noninvasively identifying molecular properties of a particular type of disease. Conventionally, such map is produced in three separate steps: 1) gene-clustering to “metagenes”, 2) image feature extraction, and 3) statistical correlation between metagenes and image features. Each step is independently performed and relies on arbitrary measurements. In this work, we investigate the potential of an end-to-end method fusing gene data with image features to generate synthetic image and learn radiogenomic map simultaneously. To achieve this goal, we develop a generative adversarial network (GAN) conditioned on both background images and gene expression profiles, synthesizing the corresponding image. Image and gene features are fused at different scales to ensure the realism and quality of the synthesized image. We tested our method on non-small cell lung cancer (NSCLC) dataset. Results demonstrate that the proposed method produces realistic synthetic images, and provides a promising way to find gene-image relationship in a holistic end-to-end manner. |
| Tasks | Image Generation |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03728v1 |
| https://arxiv.org/pdf/1907.03728v1.pdf | |
| PWC | https://paperswithcode.com/paper/correlation-via-synthesis-end-to-end-nodule |
| Repo | |
| Framework | |
An innovative adaptive kriging approach for efficient binary classification of mechanical problems
| Title | An innovative adaptive kriging approach for efficient binary classification of mechanical problems |
| Authors | Jan N. Fuhg, Amelie Fau |
| Abstract | Kriging is an efficient machine-learning tool, which allows to obtain an approximate response of an investigated phenomenon on the whole parametric space. Adaptive schemes provide a the ability to guide the experiment yielding new sample point positions to enrich the metamodel. Herein a novel adaptive scheme called Monte Carlo-intersite Voronoi (MiVor) is proposed to efficiently identify binary decision regions on the basis of a regression surrogate model. The performance of the innovative approach is tested for analytical functions as well as some mechanical problems and is furthermore compared to two regression-based adaptive schemes. For smooth problems, all three methods have comparable performances. For highly fluctuating response surface as encountered e.g. for dynamics or damage problems, the innovative MiVor algorithm performs very well and provides accurate binary classification with only a few observation points. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01490v1 |
| https://arxiv.org/pdf/1907.01490v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-innovative-adaptive-kriging-approach-for |
| Repo | |
| Framework | |
Deep Learning Captures More Accurate Diffusion Fiber Orientations Distributions than Constrained Spherical Deconvolution
| Title | Deep Learning Captures More Accurate Diffusion Fiber Orientations Distributions than Constrained Spherical Deconvolution |
| Authors | Vishwesh Nath, Kurt G. Schilling, Colin B. Hansen, Prasanna Parvathaneni, Allison E. Hainline, Camilo Bermudez, Andrew J. Plassard, Vaibhav Janve, Yurui Gao, Justin A. Blaber, Iwona Stępniewska, Adam W. Anderson, Bennett A. Landman |
| Abstract | Confocal histology provides an opportunity to establish intra-voxel fiber orientation distributions that can be used to quantitatively assess the biological relevance of diffusion weighted MRI models, e.g., constrained spherical deconvolution (CSD). Here, we apply deep learning to investigate the potential of single shell diffusion weighted MRI to explain histologically observed fiber orientation distributions (FOD) and compare the derived deep learning model with a leading CSD approach. This study (1) demonstrates that there exists additional information in the diffusion signal that is not currently exploited by CSD, and (2) provides an illustrative data-driven model that makes use of this information. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.07927v1 |
| https://arxiv.org/pdf/1911.07927v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-captures-more-accurate |
| Repo | |
| Framework | |
Small Object Detection using Context and Attention
| Title | Small Object Detection using Context and Attention |
| Authors | Jeong-Seon Lim, Marcella Astrid, Hyun-Jin Yoon, Seung-Ik Lee |
| Abstract | There are many limitations applying object detection algorithm on various environments. Especially detecting small objects is still challenging because they have low resolution and limited information. We propose an object detection method using context for improving accuracy of detecting small objects. The proposed method uses additional features from different layers as context by concatenating multi-scale features. We also propose object detection with attention mechanism which can focus on the object in image, and it can include contextual information from target layer. Experimental results shows that proposed method also has higher accuracy than conventional SSD on detecting small objects. Also, for 300$\times$300 input, we achieved 78.1% Mean Average Precision (mAP) on the PASCAL VOC2007 test set. |
| Tasks | Object Detection, Small Object Detection |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06319v2 |
| https://arxiv.org/pdf/1912.06319v2.pdf | |
| PWC | https://paperswithcode.com/paper/small-object-detection-using-context-and |
| Repo | |
| Framework | |
Singular points detection with semantic segmentation networks
| Title | Singular points detection with semantic segmentation networks |
| Authors | Jiong Chen, Heng Zhao, Zhicheng Cao, Liaojun Pang |
| Abstract | Singular points detection is one of the most classical and important problem in the field of fingerprint recognition. However, current detection rates of singular points are still unsatisfactory, especially for low-quality fingerprints. Compared with traditional image processing-based detection methods, methods based on deep learning only need the original fingerprint image but not the fingerprint orientation field. In this paper, different from other detection methods based on deep learning, we treat singular points detection as a semantic segmentation problem and just use few data for training. Furthermore, we propose a new convolutional neural network called SinNet to extract the singular regions of interest and then use a blob detection method called SimpleBlobDetector to locate the singular points. The experiments are carried out on the test dataset from SPD2010, and the proposed method has much better performance than the other advanced methods in most aspects. Compared with the state-of-art algorithms in SPD2010, our method achieves an increase of 11% in the percentage of correctly detected fingerprints and an increase of more than 18% in the core detection rate. |
| Tasks | Semantic Segmentation |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01106v1 |
| https://arxiv.org/pdf/1911.01106v1.pdf | |
| PWC | https://paperswithcode.com/paper/singular-points-detection-with-semantic |
| Repo | |
| Framework | |
Adversarial Example in Remote Sensing Image Recognition
| Title | Adversarial Example in Remote Sensing Image Recognition |
| Authors | Li Chen, Guowei Zhu, Qi Li, Haifeng Li |
| Abstract | With the wide application of remote sensing technology in various fields, the accuracy and security requirements for remote sensing images (RSIs) recognition are also increasing. In recent years, due to the rapid development of deep learning in the field of image recognition, RSI recognition models based on deep convolution neural networks (CNNs) outperform traditional hand-craft feature techniques. However, CNNs also pose security issues when they show their capability of accurate classification. By adding a very small variation of the adversarial perturbation to the input image, the CNN model can be caused to produce erroneous results with extremely high confidence, and the modification of the image is not perceived by the human eye. This added adversarial perturbation image is called an adversarial example, which poses a serious security problem for systems based on CNN model recognition results. This paper, for the first time, analyzes adversarial example problem of RSI recognition under CNN models. In the experiments, we used different attack algorithms to fool multiple high-accuracy RSI recognition models trained on multiple RSI datasets. The results show that RSI recognition models are also vulnerable to adversarial examples, and the models with different structures trained on the same RSI dataset also have different vulnerabilities. For each RSI dataset, the number of features also affects the vulnerability of the model. Many features are good for defensive adversarial examples. Further, we find that the attacked class of RSI has an attack selectivity property. The misclassification of adversarial examples of the RSIs are related to the similarity of the original classes in the CNN feature space. In addition, adversarial examples in RSI recognition are of great significance for the security of remote sensing applications, showing a huge potential for future research. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13222v2 |
| https://arxiv.org/pdf/1910.13222v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-example-in-remote-sensing-image |
| Repo | |
| Framework | |
Fully-Asynchronous Fully-Implicit Variable-Order Variable-Timestep Simulation of Neural Networks
| Title | Fully-Asynchronous Fully-Implicit Variable-Order Variable-Timestep Simulation of Neural Networks |
| Authors | Bruno Magalhães, Michael Hines, Thomas Sterling, Felix Schuermann |
| Abstract | State-of-the-art simulations of detailed neural models follow the Bulk Synchronous Parallel execution model. Execution is divided in equidistant communication intervals, equivalent to the shortest synaptic delay in the network. Neurons stepping is performed independently, with collective communication guiding synchronization and exchange of synaptic events. The interpolation step size is fixed and chosen based on some prior knowledge of the fastest possible dynamics in the system. However, simulations driven by stiff dynamics or a wide range of time scales - such as multiscale simulations of neural networks - struggle with fixed step interpolation methods, yielding excessive computation of intervals of quasi-constant activity, inaccurate interpolation of periods of high volatility solution, and being incapable of handling unknown or distinct time constants. A common alternative is the usage of adaptive stepping methods, however they have been deemed inefficient in parallel executions due to computational load imbalance at the synchronization barriers that characterize the BSP execution model. We introduce a distributed fully-asynchronous execution model that removes global synchronization, allowing for longer variable timestep interpolations. Asynchronicity is provided by active point-to-point communication notifying neurons’ time advancement to synaptic connectivities. Time stepping is driven by scheduled neuron advancements based on synaptic delays across neurons, yielding an “exhaustive yet not speculative” adaptive-step execution. Execution benchmarks on 64 Cray XE6 compute nodes demonstrate a reduced number of interpolation steps, higher numerical accuracy and lower time to solution, compared to state-of-the-art methods. Efficiency is shown to be activity-dependent, with scaling of the algorithm demonstrated on a simulation of a laboratory experiment. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00670v2 |
| https://arxiv.org/pdf/1907.00670v2.pdf | |
| PWC | https://paperswithcode.com/paper/fully-asynchronous-fully-implicit-variable |
| Repo | |
| Framework | |
Linear algorithm for solution n-Queens Completion problem
| Title | Linear algorithm for solution n-Queens Completion problem |
| Authors | E. Grigoryan |
| Abstract | A linear algorithm is described for solving the n-Queens Completion problem for an arbitrary composition of k queens, consistently distributed on a chessboard of size n x n. Two important rules are used in the algorithm: a) the rule of sequential risk elimination for the entire system as a whole; b) the rule of formation of minimal damage in the given selection conditions. For any composition of k queens (1<= k<n), a solution is provided, or a decision is made that this composition can’t be completed. The probability of an error in making such a decision does not exceed 0.0001, and its value decreases, with increasing n. It is established that the average time, required for the queen to be placed on one row, decreases with increasing value of n. A description is given of two random selection models and the results of their comparative analysis. A model for organizing the Back Tracking procedure is proposed based on the separation of the solution matrix into two basic levels. Regression formulas are given for the dependence of basic levels on the value of n. It was found that for n=(7-100000) the number of solutions in which the Back Tracking procedure has never been used exceeds 35%. Moreover, for n=(320-22500), the number of such cases exceeds 50 %. A quick algorithm for verifying the correctness of n-Queens problem solution or arbitrary composition of k queens is given. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.05935v2 |
| https://arxiv.org/pdf/1912.05935v2.pdf | |
| PWC | https://paperswithcode.com/paper/linear-algorithm-for-solutions-n-queens |
| Repo | |
| Framework | |
Modeling the Chlorophyll-a from Sea Surface Reflectance in West Africa by Deep Learning Methods: A Comparison of Multiple Algorithms
| Title | Modeling the Chlorophyll-a from Sea Surface Reflectance in West Africa by Deep Learning Methods: A Comparison of Multiple Algorithms |
| Authors | Daouda Diouf, Djibril Seck |
| Abstract | Deep learning provide successful applications in many fields. Recently, machines learning are involved for oceans remote sensing applications. In this study, we use and compare about eight (8) deep learning estimators for retrieval of a mainly pigment of phytoplankton. Depending on the water case and the multiple instruments simultaneouslyobserving the earth on a variety of platforms, several algorithm are used to estimate the chlolophyll-a from marine reflectance. By using a long-term multi-sensor time-series of satellite ocean-colour data, as MODIS, SeaWifs, VIIRS, MERIS, etc, we make a unique deep network model able to establish a relationship between sea surface reflectance and chlorophyll-a from any measurement satellite sensor over West Africa. These data fusion take into account the bias between case water and instruments. We construct several chlorophyll-a concentration prediction deep learning based models, compare them and therefore use the best for our study. Results obtained for accuracy training and test are quite good. The mean absolute error are very low and vary between 0,07 to 0,13 mg/m3. |
| Tasks | Time Series |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03216v1 |
| https://arxiv.org/pdf/1912.03216v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-the-chlorophyll-a-from-sea-surface |
| Repo | |
| Framework | |
Curiosity-Driven Multi-Criteria Hindsight Experience Replay
| Title | Curiosity-Driven Multi-Criteria Hindsight Experience Replay |
| Authors | John B. Lanier, Stephen McAleer, Pierre Baldi |
| Abstract | Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the prediction error of a learned dynamics model as an intrinsic reward has been shown to be effective for exploring a number of sparse-reward environments. We present a method that combines hindsight with curiosity-driven exploration and curriculum learning in order to solve the challenging sparse-reward block stacking task. We are the first to stack more than two blocks using only sparse reward without human demonstrations. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03710v1 |
| https://arxiv.org/pdf/1906.03710v1.pdf | |
| PWC | https://paperswithcode.com/paper/curiosity-driven-multi-criteria-hindsight |
| Repo | |
| Framework | |
Improving Generalization and Stability of Generative Adversarial Networks
| Title | Improving Generalization and Stability of Generative Adversarial Networks |
| Authors | Hoang Thanh-Tung, Truyen Tran, Svetha Venkatesh |
| Abstract | Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we analyze the generalization of GANs in practical settings. We show that discriminators trained on discrete datasets with the original GAN loss have poor generalization capability and do not approximate the theoretically optimal discriminator. We propose a zero-centered gradient penalty for improving the generalization of the discriminator by pushing it toward the optimal discriminator. The penalty guarantees the generalization and convergence of GANs. Experiments on synthetic and large scale datasets verify our theoretical analysis. |
| Tasks | |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.03984v1 |
| http://arxiv.org/pdf/1902.03984v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-generalization-and-stability-of |
| Repo | |
| Framework | |
