October 19, 2019

3296 words 16 mins read

Paper Group ANR 200

Using 3D Hahn Moments as A Computational Representation of ATS Drugs Molecular Structure. Cartoon-to-real: An Approach to Translate Cartoon to Realistic Images using GAN. Learning Attentional Communication for Multi-Agent Cooperation. Progressive Spatial Recurrent Neural Network for Intra Prediction. A Unified Deep Learning Architecture for Abuse D …

Using 3D Hahn Moments as A Computational Representation of ATS Drugs Molecular Structure


Title	Using 3D Hahn Moments as A Computational Representation of ATS Drugs Molecular Structure
Authors	Satrya Fajri Pratama, Azah Kamilah Muda, Yun-Huoy Choo, Ramon Carbó-Dorca, Ajith Abraham
Abstract	The campaign against drug abuse is fought by all countries, most notably on ATS drugs. The technical limitations of the current test kits to detect new brand of ATS drugs present a challenge to law enforcement authorities and forensic laboratories. Meanwhile, new molecular imaging devices which allowed mankind to characterize the physical 3D molecular structure have been recently introduced, and it can be used to remedy the limitations of existing drug test kits. Thus, a new type of 3D molecular structure representation technique should be developed to cater the 3D molecular structure acquired physically using these molecular imaging devices. One of the applications of image processing methods to represent a 3D image is 3D moments, and this study formulates a new 3D moments technique, namely 3D Hahn moments, to represent the 3D molecular structure of ATS drugs. The performance of the proposed technique was analysed using drug chemical structures obtained from UNODC for the ATS drugs, while non-ATS drugs are obtained randomly from ChemSpider database. The evaluation shows the technique is qualified to be further explored in the future works to be fully compatible with ATS drug identification domain.
Tasks
Published	2018-02-18
URL	http://arxiv.org/abs/1802.06404v2
PDF	http://arxiv.org/pdf/1802.06404v2.pdf
PWC	https://paperswithcode.com/paper/using-3d-hahn-moments-as-a-computational
Repo
Framework

Cartoon-to-real: An Approach to Translate Cartoon to Realistic Images using GAN


Title	Cartoon-to-real: An Approach to Translate Cartoon to Realistic Images using GAN
Authors	K M Arefeen Sultan, Labiba Kanij Rupty, Nahidul Islam Pranto, Sayed Khan Shuvo, Mohammad Imrul Jubair
Abstract	We propose a method to translate cartoon images to real world images using Generative Aderserial Network (GAN). Existing GAN-based image-to-image translation methods which are trained on paired datasets are impractical as the data is difficult to accumulate. Therefore, in this paper we exploit the Cycle-Consistent Adversarial Networks (CycleGAN) method for images translation which needs an unpaired dataset. By applying CycleGAN we show that our model is able to generate meaningful real world images from cartoon images. However, we implement another state of the art technique $-$ Deep Analogy $-$ to compare the performance of our approach.
Tasks	Cartoon-To-Real Translation, Image-to-Image Translation
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11796v3
PDF	http://arxiv.org/pdf/1811.11796v3.pdf
PWC	https://paperswithcode.com/paper/cartoon-to-real-an-approach-to-translate
Repo
Framework

Learning Attentional Communication for Multi-Agent Cooperation


Title	Learning Attentional Communication for Multi-Agent Cooperation
Authors	Jiechuan Jiang, Zongqing Lu
Abstract	Communication could potentially be an effective way for multi-agent cooperation. However, information sharing among all agents or in predefined communication architectures that existing methods adopt can be problematic. When there is a large number of agents, agents cannot differentiate valuable information that helps cooperative decision making from globally shared information. Therefore, communication barely helps, and could even impair the learning of multi-agent cooperation. Predefined communication architectures, on the other hand, restrict communication among agents and thus restrain potential cooperation. To tackle these difficulties, in this paper, we propose an attentional communication model that learns when communication is needed and how to integrate shared information for cooperative decision making. Our model leads to efficient and effective communication for large-scale multi-agent cooperation. Empirically, we show the strength of our model in a variety of cooperative scenarios, where agents are able to develop more coordinated and sophisticated strategies than existing methods.
Tasks	Decision Making
Published	2018-05-20
URL	http://arxiv.org/abs/1805.07733v3
PDF	http://arxiv.org/pdf/1805.07733v3.pdf
PWC	https://paperswithcode.com/paper/learning-attentional-communication-for-multi
Repo
Framework

Progressive Spatial Recurrent Neural Network for Intra Prediction


Title	Progressive Spatial Recurrent Neural Network for Intra Prediction
Authors	Yueyu Hu, Wenhan Yang, Mading Li, Jiaying Liu
Abstract	Intra prediction is an important component of modern video codecs, which is able to efficiently squeeze out the spatial redundancy in video frames. With preceding pixels as the context, traditional intra prediction schemes generate linear predictions based on several predefined directions (i.e. modes) for blocks to be encoded. However, these modes are relatively simple and their predictions may fail when facing blocks with complex textures, which leads to additional bits encoding the residue. In this paper, we design a Progressive Spatial Recurrent Neural Network (PS-RNN) that learns to conduct intra prediction. Specifically, our PS-RNN consists of three spatial recurrent units and progressively generates predictions by passing information along from preceding contents to blocks to be encoded. To make our network generate predictions considering both distortion and bit-rate, we propose to use Sum of Absolute Transformed Difference (SATD) as the loss function to train PS-RNN since SATD is able to measure rate-distortion cost of encoding a residue block. Moreover, our method supports variable-block-size for intra prediction, which is more practical in real coding conditions. The proposed intra prediction scheme achieves on average 2.5% bit-rate reduction on variable-block-size settings under the same reconstruction quality compared with HEVC.
Tasks
Published	2018-07-06
URL	https://arxiv.org/abs/1807.02232v2
PDF	https://arxiv.org/pdf/1807.02232v2.pdf
PWC	https://paperswithcode.com/paper/progressive-spatial-recurrent-neural-network
Repo
Framework

A Unified Deep Learning Architecture for Abuse Detection


Title	A Unified Deep Learning Architecture for Abuse Detection
Authors	Antigoni-Maria Founta, Despoina Chatzakou, Nicolas Kourtellis, Jeremy Blackburn, Athena Vakali, Ilias Leontiadis
Abstract	Hate speech, offensive language, sexism, racism and other types of abusive behavior have become a common phenomenon in many online social media platforms. In recent years, such diverse abusive behaviors have been manifesting with increased frequency and levels of intensity. This is due to the openness and willingness of popular media platforms, such as Twitter and Facebook, to host content of sensitive or controversial topics. However, these platforms have not adequately addressed the problem of online abusive behavior, and their responsiveness to the effective detection and blocking of such inappropriate behavior remains limited. In the present paper, we study this complex problem by following a more holistic approach, which considers the various aspects of abusive behavior. To make the approach tangible, we focus on Twitter data and analyze user and textual properties from different angles of abusive posting behavior. We propose a deep learning architecture, which utilizes a wide variety of available metadata, and combines it with automatically-extracted hidden patterns within the text of the tweets, to detect multiple abusive behavioral norms which are highly inter-related. We apply this unified architecture in a seamless, transparent fashion to detect different types of abusive behavior (hate speech, sexism vs. racism, bullying, sarcasm, etc.) without the need for any tuning of the model architecture for each task. We test the proposed approach with multiple datasets addressing different and multiple abusive behaviors on Twitter. Our results demonstrate that it largely outperforms the state-of-art methods (between 21 and 45% improvement in AUC, depending on the dataset).
Tasks	Abuse Detection
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00385v2
PDF	http://arxiv.org/pdf/1802.00385v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-deep-learning-architecture-for
Repo
Framework

Semi-supervised Seizure Prediction with Generative Adversarial Networks


Title	Semi-supervised Seizure Prediction with Generative Adversarial Networks
Authors	Nhan Duy Truong, Levin Kuhlmann, Mohammad Reza Bonyadi, Omid Kavehei
Abstract	In this article, we propose an approach that can make use of not only labeled EEG signals but also the unlabeled ones which is more accessible. We also suggest the use of data fusion to further improve the seizure prediction accuracy. Data fusion in our vision includes EEG signals, cardiogram signals, body temperature and time. We use the short-time Fourier transform on 28-s EEG windows as a pre-processing step. A generative adversarial network (GAN) is trained in an unsupervised manner where information of seizure onset is disregarded. The trained Discriminator of the GAN is then used as feature extractor. Features generated by the feature extractor are classified by two fully-connected layers (can be replaced by any classifier) for the labeled EEG signals. This semi-supervised seizure prediction method achieves area under the operating characteristic curve (AUC) of 77.68% and 75.47% for the CHBMIT scalp EEG dataset and the Freiburg Hospital intracranial EEG dataset, respectively. Unsupervised training without the need of labeling is important because not only it can be performed in real-time during EEG signal recording, but also it does not require feature engineering effort for each patient.
Tasks	EEG, Feature Engineering, Seizure prediction
Published	2018-06-20
URL	http://arxiv.org/abs/1806.08235v1
PDF	http://arxiv.org/pdf/1806.08235v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-seizure-prediction-with
Repo
Framework

Semi-Supervised Classification for oil reservoir


Title	Semi-Supervised Classification for oil reservoir
Authors	Yanan Li, Haixiang Guo, Andrew P Paplinski
Abstract	This paper addresses the general problem of accurate identification of oil reservoirs. Recent improvements in well or borehole logging technology have resulted in an explosive amount of data available for processing. The traditional methods of analysis of the logs characteristics by experts require significant amount of time and money and is no longer practicable. In this paper, we use the semi-supervised learning to solve the problem of ever-increasing amount of unlabelled data available for interpretation. The experts are needed to label only a small amount of the log data. The neural network classifier is first trained with the initial labelled data. Next, batches of unlabelled data are being classified and the samples with the very high class probabilities are being used in the next training session, bootstrapping the classifier. The process of training, classifying, enhancing the labelled data is repeated iteratively until the stopping criteria are met, that is, no more high probability samples are found. We make an empirical study on the well data from Jianghan oil field and test the performance of the neural network semi-supervised classifier. We compare this method with other classifiers. The comparison results show that our neural network semi-supervised classifier is superior to other classification methods.
Tasks
Published	2018-04-05
URL	http://arxiv.org/abs/1804.01675v1
PDF	http://arxiv.org/pdf/1804.01675v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-classification-for-oil
Repo
Framework

Learning Semantic Segmentation with Diverse Supervision


Title	Learning Semantic Segmentation with Diverse Supervision
Authors	Linwei Ye, Zhi Liu, Yang Wang
Abstract	Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very costly and time-consuming to collect. In this paper, we propose a method for learning CNN-based semantic segmentation models from images with several types of annotations that are available for various computer vision tasks, including image-level labels for classification, box-level labels for object detection and pixel-level labels for semantic segmentation. The proposed method is flexible and can be used together with any existing CNN-based semantic segmentation networks. Experimental evaluation on the challenging PASCAL VOC 2012 and SIFT-flow benchmarks demonstrate that the proposed method can effectively make use of diverse training data to improve the performance of the learned models.
Tasks	Object Detection, Semantic Segmentation
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00509v1
PDF	http://arxiv.org/pdf/1802.00509v1.pdf
PWC	https://paperswithcode.com/paper/learning-semantic-segmentation-with-diverse
Repo
Framework

Image Manipulation with Perceptual Discriminators


Title	Image Manipulation with Perceptual Discriminators
Authors	Diana Sungatullina, Egor Zakharov, Dmitry Ulyanov, Victor Lempitsky
Abstract	Systems that perform image manipulation using deep convolutional networks have achieved remarkable realism. Perceptual losses and losses based on adversarial discriminators are the two main classes of learning objectives behind these advances. In this work, we show how these two ideas can be combined in a principled and non-additive manner for unaligned image translation tasks. This is accomplished through a special architecture of the discriminator network inside generative adversarial learning framework. The new architecture, that we call a perceptual discriminator, embeds the convolutional parts of a pre-trained deep classification network inside the discriminator network. The resulting architecture can be trained on unaligned image datasets while benefiting from the robustness and efficiency of perceptual losses. We demonstrate the merits of the new architecture in a series of qualitative and quantitative comparisons with baseline approaches and state-of-the-art frameworks for unaligned image translation.
Tasks
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01396v1
PDF	http://arxiv.org/pdf/1809.01396v1.pdf
PWC	https://paperswithcode.com/paper/image-manipulation-with-perceptual
Repo
Framework

cuPC: CUDA-based Parallel PC Algorithm for Causal Structure Learning on GPU


Title	cuPC: CUDA-based Parallel PC Algorithm for Causal Structure Learning on GPU
Authors	Behrooz Zarebavani, Foad Jafarinejad, Matin Hashemi, Saber Salehkaleybar
Abstract	The main goal in many fields in the empirical sciences is to discover causal relationships among a set of variables from observational data. PC algorithm is one of the promising solutions to learn underlying causal structure by performing a number of conditional independence tests. In this paper, we propose a novel GPU-based parallel algorithm, called cuPC, to execute an order-independent version of PC. The proposed solution has two variants, cuPC-E and cuPC-S, which parallelize PC in two different ways for multivariate normal distribution. Experimental results show the scalability of the proposed algorithms with respect to the number of variables, the number of samples, and different graph densities. For instance, in one of the most challenging datasets, the runtime is reduced from more than 11 hours to about 4 seconds. On average, cuPC-E and cuPC-S achieve 500 X and 1300 X speedup, respectively, compared to serial implementation on CPU. The source code of cuPC is available online [1].
Tasks
Published	2018-12-20
URL	https://arxiv.org/abs/1812.08491v4
PDF	https://arxiv.org/pdf/1812.08491v4.pdf
PWC	https://paperswithcode.com/paper/cupc-cuda-based-parallel-pc-algorithm-for
Repo
Framework

Training Big Random Forests with Little Resources


Title	Training Big Random Forests with Little Resources
Authors	Fabian Gieseke, Christian Igel
Abstract	Without access to large compute clusters, building random forests on large datasets is still a challenging problem. This is, in particular, the case if fully-grown trees are desired. We propose a simple yet effective framework that allows to efficiently construct ensembles of huge trees for hundreds of millions or even billions of training instances using a cheap desktop computer with commodity hardware. The basic idea is to consider a multi-level construction scheme, which builds top trees for small random subsets of the available data and which subsequently distributes all training instances to the top trees’ leaves for further processing. While being conceptually simple, the overall efficiency crucially depends on the particular implementation of the different phases. The practical merits of our approach are demonstrated using dense datasets with hundreds of millions of training instances.
Tasks
Published	2018-02-18
URL	http://arxiv.org/abs/1802.06394v1
PDF	http://arxiv.org/pdf/1802.06394v1.pdf
PWC	https://paperswithcode.com/paper/training-big-random-forests-with-little
Repo
Framework

Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism


Title	Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism
Authors	Zhengchao Zhang, Meng Li, Xi Lin, Yinhai Wang, Fang He
Abstract	Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial dependency in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In the proposed deep learning framework, spatial and temporal dependencies are modeled through the Seq2Seq model and graph convolution network separately, and the attention mechanism along with a newly designed training method based on the Seq2Seq architecture is proposed to overcome the difficulty in multistep prediction and further capture the temporal heterogeneity of traffic pattern. We conduct numerical tests to compare AGC-Seq2Seq with other benchmark models using a real-world dataset. The results indicate that our model yields the best prediction performance in terms of various prediction error measures. Furthermore, the variation of spatiotemporal correlation of traffic conditions under different perdition steps and road segments is revealed through sensitivity analyses.
Tasks
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10237v1
PDF	http://arxiv.org/pdf/1810.10237v1.pdf
PWC	https://paperswithcode.com/paper/multistep-speed-prediction-on-traffic
Repo
Framework

Helping each Other: A Framework for Customer-to-Customer Suggestion Mining using a Semi-supervised Deep Neural Network


Title	Helping each Other: A Framework for Customer-to-Customer Suggestion Mining using a Semi-supervised Deep Neural Network
Authors	Hitesh Golchha, Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya
Abstract	Suggestion mining is increasingly becoming an important task along with sentiment analysis. In today’s cyberspace world, people not only express their sentiments and dispositions towards some entities or services, but they also spend considerable time sharing their experiences and advice to fellow customers and the product/service providers with two-fold agenda: helping fellow customers who are likely to share a similar experience, and motivating the producer to bring specific changes in their offerings which would be more appreciated by the customers. In our current work, we propose a hybrid deep learning model to identify whether a review text contains any suggestion. The model employs semi-supervised learning to leverage the useful information from the large amount of unlabeled data. We evaluate the performance of our proposed model on a benchmark customer review dataset, comprising of the reviews of Hotel and Electronics domains. Our proposed approach shows the F-scores of 65.6% and 65.5% for the Hotel and Electronics review datasets, respectively. These performances are significantly better compared to the existing state-of-the-art system.
Tasks	Sentiment Analysis
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00379v1
PDF	http://arxiv.org/pdf/1811.00379v1.pdf
PWC	https://paperswithcode.com/paper/helping-each-other-a-framework-for-customer
Repo
Framework

Practical bounds on the error of Bayesian posterior approximations: A nonasymptotic approach


Title	Practical bounds on the error of Bayesian posterior approximations: A nonasymptotic approach
Authors	Jonathan H. Huggins, Trevor Campbell, Mikołaj Kasprzak, Tamara Broderick
Abstract	Bayesian inference typically requires the computation of an approximation to the posterior distribution. An important requirement for an approximate Bayesian inference algorithm is to output high-accuracy posterior mean and uncertainty estimates. Classical Monte Carlo methods, particularly Markov Chain Monte Carlo, remain the gold standard for approximate Bayesian inference because they have a robust finite-sample theory and reliable convergence diagnostics. However, alternative methods, which are more scalable or apply to problems where Markov Chain Monte Carlo cannot be used, lack the same finite-data approximation theory and tools for evaluating their accuracy. In this work, we develop a flexible new approach to bounding the error of mean and uncertainty estimates of scalable inference algorithms. Our strategy is to control the estimation errors in terms of Wasserstein distance, then bound the Wasserstein distance via a generalized notion of Fisher distance. Unlike computing the Wasserstein distance, which requires access to the normalized posterior distribution, the Fisher distance is tractable to compute because it requires access only to the gradient of the log posterior density. We demonstrate the usefulness of our Fisher distance approach by deriving bounds on the Wasserstein error of the Laplace approximation and Hilbert coresets. We anticipate that our approach will be applicable to many other approximate inference methods such as the integrated Laplace approximation, variational inference, and approximate Bayesian computation
Tasks	Bayesian Inference
Published	2018-09-25
URL	http://arxiv.org/abs/1809.09505v2
PDF	http://arxiv.org/pdf/1809.09505v2.pdf
PWC	https://paperswithcode.com/paper/practical-bounds-on-the-error-of-bayesian
Repo
Framework

Robust Anomaly-Based Ship Proposals Detection from Pan-sharpened High-Resolution Satellite Image


Title	Robust Anomaly-Based Ship Proposals Detection from Pan-sharpened High-Resolution Satellite Image
Authors	Viet Hung Luu, Nguyen Hoang Hoa Luong, Quang Hung Bui, Thi Nhat Thanh Nguyen
Abstract	Pre-screening of ship proposals is now employed by top ship detectors to avoid exhaustive search across image. In very high resolution (VHR) optical image, ships appeared as a cluster of abnormal bright pixels in open sea clutter (noise-like background). Anomaly-based detector utilizing Panchromatic (PAN) data has been widely used in many researches to detect ships, however, still facing two main drawbacks: 1) detection rate tend to be low particularly when a ship is low contrast and 2) these models require a high manual configuration to select a threshold value best separate ships from sea surface background. This paper aims at further investigation of anomaly-based model to solve those issues. First, pan-sharpened Multi Spectral (MS) data is incorporated together with PAN to enhance ship discrimination. Second, we propose an improved anomaly-based model combining both global intensity anomaly and local texture anomaly map. Regarding noise appeared due to the present of sea clutter and because of pan-sharpen process, texture abnormality suppression term based on quantization theory is introduced. Experimental results on VNREDSat-1 VHR optical satellite images suggest that the pan-sharpened near-infrared (P-NIR) band can improve discrimination of ships from surrounding waters. Compared to state-of-the-art anomaly-based detectors, our proposed anomaly-based model on the combination of PAN and P-NIR data cannot only achieved highest ship detection’s recall rate (91.14% and 45.9% on high-contrast and low-contrast dataset respectively) but also robust to different automatic threshold selection techniques.
Tasks	Quantization
Published	2018-04-25
URL	http://arxiv.org/abs/1804.09322v1
PDF	http://arxiv.org/pdf/1804.09322v1.pdf
PWC	https://paperswithcode.com/paper/robust-anomaly-based-ship-proposals-detection
Repo
Framework