October 19, 2019

2706 words 13 mins read

Paper Group ANR 329

Automatic Clustering of a Network Protocol with Weakly-Supervised Clustering. Adaptive Quantum State Tomography with Neural Networks. Neural Open Information Extraction. Using transfer learning to detect galaxy mergers. Addressing Training Bias via Automated Image Annotation. Noise-resistant Deep Learning for Object Classification in 3D Point Cloud …

Automatic Clustering of a Network Protocol with Weakly-Supervised Clustering


Title	Automatic Clustering of a Network Protocol with Weakly-Supervised Clustering
Authors	Tobias Schrank, Franz Pernkopf
Abstract	Abstraction is a fundamental part when learning behavioral models of systems. Usually the process of abstraction is manually defined by domain experts. This paper presents a method to perform automatic abstraction for network protocols. In particular a weakly supervised clustering algorithm is used to build an abstraction with a small vocabulary size for the widely used TLS protocol. To show the effectiveness of the proposed method we compare the resultant abstract messages to a manually constructed (reference) abstraction. With a small amount of side-information in the form of a few labeled examples this method finds an abstraction that matches the reference abstraction perfectly.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00981v1
PDF	http://arxiv.org/pdf/1806.00981v1.pdf
PWC	https://paperswithcode.com/paper/automatic-clustering-of-a-network-protocol
Repo
Framework

Adaptive Quantum State Tomography with Neural Networks


Title	Adaptive Quantum State Tomography with Neural Networks
Authors	Yihui Quek, Stanislav Fort, Hui Khoon Ng
Abstract	Quantum State Tomography is the task of determining an unknown quantum state by making measurements on identical copies of the state. Current algorithms are costly both on the experimental front – requiring vast numbers of measurements – as well as in terms of the computational time to analyze those measurements. In this paper, we address the problem of analysis speed and flexibility, introducing \textit{Neural Adaptive Quantum State Tomography} (NA-QST), a machine learning based algorithm for quantum state tomography that adapts measurements and provides orders of magnitude faster processing while retaining state-of-the-art reconstruction accuracy. Our algorithm is inspired by particle swarm optimization and Bayesian particle-filter based adaptive methods, which we extend and enhance using neural networks. The resampling step, in which a bank of candidate solutions – particles – is refined, is in our case learned directly from data, removing the computational bottleneck of standard methods. We successfully replace the Bayesian calculation that requires computational time of $O(\mathrm{poly}(n))$ with a learned heuristic whose time complexity empirically scales as $O(\log(n))$ with the number of copies measured $n$, while retaining the same reconstruction accuracy. This corresponds to a factor of a million speedup for $10^7$ copies measured. We demonstrate that our algorithm learns to work with basis, symmetric informationally complete (SIC), as well as other types of POVMs. We discuss the value of measurement adaptivity for each POVM type, demonstrating that its effect is significant only for basis POVMs. Our algorithm can be retrained within hours on a single laptop for a two-qubit situation, which suggests a feasible time-cost when extended to larger systems. It can also adapt to a subset of possible states, a choice of the type of measurement, and other experimental details.
Tasks	Quantum State Tomography
Published	2018-12-17
URL	http://arxiv.org/abs/1812.06693v1
PDF	http://arxiv.org/pdf/1812.06693v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-quantum-state-tomography-with-neural
Repo
Framework

Neural Open Information Extraction


Title	Neural Open Information Extraction
Authors	Lei Cui, Furu Wei, Ming Zhou
Abstract	Conventional Open Information Extraction (Open IE) systems are usually built on hand-crafted patterns from other NLP tools such as syntactic parsing, yet they face problems of error propagation. In this paper, we propose a neural Open IE approach with an encoder-decoder framework. Distinct from existing methods, the neural Open IE approach learns highly confident arguments and relation tuples bootstrapped from a state-of-the-art Open IE system. An empirical study on a large benchmark dataset shows that the neural Open IE system significantly outperforms several baselines, while maintaining comparable computational efficiency.
Tasks	Open Information Extraction
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04270v1
PDF	http://arxiv.org/pdf/1805.04270v1.pdf
PWC	https://paperswithcode.com/paper/neural-open-information-extraction
Repo
Framework

Using transfer learning to detect galaxy mergers


Title	Using transfer learning to detect galaxy mergers
Authors	Sandro Ackermann, Kevin Schawinski, Ce Zhang, Anna K. Weigel, M. Dennis Turp
Abstract	We investigate the use of deep convolutional neural networks (deep CNNs) for automatic visual detection of galaxy mergers. Moreover, we investigate the use of transfer learning in conjunction with CNNs, by retraining networks first trained on pictures of everyday objects. We test the hypothesis that transfer learning is useful for improving classification performance for small training sets. This would make transfer learning useful for finding rare objects in astronomical imaging datasets. We find that these deep learning methods perform significantly better than current state-of-the-art merger detection methods based on nonparametric systems like CAS and GM$_{20}$. Our method is end-to-end and robust to image noise and distortions; it can be applied directly without image preprocessing. We also find that transfer learning can act as a regulariser in some cases, leading to better overall classification accuracy ($p = 0.02$). Transfer learning on our full training set leads to a lowered error rate from 0.038 $\pm$ 1 down to 0.032 $\pm$ 1, a relative improvement of 15%. Finally, we perform a basic sanity-check by creating a merger sample with our method, and comparing with an already existing, manually created merger catalogue in terms of colour-mass distribution and stellar mass function.
Tasks	Transfer Learning
Published	2018-05-25
URL	http://arxiv.org/abs/1805.10289v2
PDF	http://arxiv.org/pdf/1805.10289v2.pdf
PWC	https://paperswithcode.com/paper/using-transfer-learning-to-detect-galaxy
Repo
Framework

Addressing Training Bias via Automated Image Annotation


Title	Addressing Training Bias via Automated Image Annotation
Authors	Zhujun Xiao, Yanzi Zhu, Yuxin Chen, Ben Y. Zhao, Junchen Jiang, Haitao Zheng
Abstract	Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization, working in unison with cameras, can produce automated annotation of targets on images and videos captured in the wild. Using pedestrian and vehicle detection as examples, we demonstrate the feasibility, benefits, and challenges of an automatic image annotation system. Our work calls for new technical development on passive localization, mobile data analytics, and error-resilient ML models, as well as design issues in user privacy policies.
Tasks
Published	2018-09-22
URL	http://arxiv.org/abs/1809.10242v2
PDF	http://arxiv.org/pdf/1809.10242v2.pdf
PWC	https://paperswithcode.com/paper/addressing-training-bias-via-automated-image
Repo
Framework

Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor


Title	Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor
Authors	Dmytro Bobkov, Sili Chen, Ruiqing Jian, Muhammad Iqbal, Eckehard Steinbach
Abstract	Object retrieval and classification in point cloud data is challenged by noise, irregular sampling density and occlusion. To address this issue, we propose a point pair descriptor that is robust to noise and occlusion and achieves high retrieval accuracy. We further show how the proposed descriptor can be used in a 4D convolutional neural network for the task of object classification. We propose a novel 4D convolutional layer that is able to learn class-specific clusters in the descriptor histograms. Finally, we provide experimental validation on 3 benchmark datasets, which confirms the superiority of the proposed approach.
Tasks	Object Classification
Published	2018-04-05
URL	http://arxiv.org/abs/1804.02077v1
PDF	http://arxiv.org/pdf/1804.02077v1.pdf
PWC	https://paperswithcode.com/paper/noise-resistant-deep-learning-for-object
Repo
Framework

Salient Region Segmentation


Title	Salient Region Segmentation
Authors	Sen He, Nicolas Pugeault
Abstract	Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough, a new cohort of models were proposed based on neural network architectures, allowing significantly higher gaze prediction than previous shallow models, on all metrics. However, most models treat the saliency prediction as a \textit{regression} problem, and accurate regression of high-dimensional data is known to be a hard problem. Furthermore, it is unclear that intermediate levels of saliency (ie, neither very high, nor very low) are meaningful: Something is either salient, or it is not. Drawing from those two observations, we reformulate the saliency prediction problem as a salient region \textit{segmentation} problem. We demonstrate that the reformulation allows for faster convergence than the classical regression problem, while performance is comparable to state-of-the-art. We also visualise the general features learned by the model, which are showed to be consistent with insights from psychophysics.
Tasks	Gaze Prediction, Saliency Prediction
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05759v1
PDF	http://arxiv.org/pdf/1803.05759v1.pdf
PWC	https://paperswithcode.com/paper/salient-region-segmentation
Repo
Framework

Efficient Bayesian Inference for a Gaussian Process Density Model


Title	Efficient Bayesian Inference for a Gaussian Process Density Model
Authors	Christian Donner, Manfred Opper
Abstract	We reconsider a nonparametric density model based on Gaussian processes. By augmenting the model with latent P'olya–Gamma random variables and a latent marked Poisson process we obtain a new likelihood which is conjugate to the model’s Gaussian process prior. The augmented posterior allows for efficient inference by Gibbs sampling and an approximate variational mean field approach. For the latter we utilise sparse GP approximations to tackle the infinite dimensionality of the problem. The performance of both algorithms and comparisons with other density estimators are demonstrated on artificial and real datasets with up to several thousand data points.
Tasks	Bayesian Inference, Gaussian Processes
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11494v1
PDF	http://arxiv.org/pdf/1805.11494v1.pdf
PWC	https://paperswithcode.com/paper/efficient-bayesian-inference-for-a-gaussian
Repo
Framework

Framework for Opinion Mining Approach to Augment Education System Performance


Title	Framework for Opinion Mining Approach to Augment Education System Performance
Authors	Amritpal Kaur, Harkiran Kaur
Abstract	The extensive expansion growth of social networking sites allows the people to share their views and experiences freely with their peers on internet. Due to this, huge amount of data is generated on everyday basis which can be used for the opinion mining to extract the views of people in a particular field. Opinion mining finds its applications in many areas such as Tourism, Politics, education and entertainment, etc. It has not been extensively implemented in area of education system. This paper discusses the malpractices in the present examination system. In the present scenario, Opinion mining is vastly used for decision making. The authors of this paper have designed a framework by applying Na"ive Bayes approach to the education dataset. The various phases of Na"ive Bayes approach include three steps: conversion of data into frequency table, making classes of dataset and apply the Na"ive Bayes algorithm equation to calculate the probabilities of classes. Finally the highest probability class is the outcome of this prediction. These predictions are used to make improvements in the education system and help to provide better education.
Tasks	Decision Making, Opinion Mining
Published	2018-06-25
URL	http://arxiv.org/abs/1806.09279v1
PDF	http://arxiv.org/pdf/1806.09279v1.pdf
PWC	https://paperswithcode.com/paper/framework-for-opinion-mining-approach-to
Repo
Framework

Addition of Code Mixed Features to Enhance the Sentiment Prediction of Song Lyrics


Title	Addition of Code Mixed Features to Enhance the Sentiment Prediction of Song Lyrics
Authors	Gangula Rama Rohit Reddy, Radhika Mamidi
Abstract	Sentiment analysis, also called opinion mining, is the field of study that analyzes people’s opinions,sentiments, attitudes and emotions. Songs are important to sentiment analysis since the songs and mood are mutually dependent on each other. Based on the selected song it becomes easy to find the mood of the listener, in future it can be used for recommendation. The song lyric is a rich source of datasets containing words that are helpful in analysis and classification of sentiments generated from it. Now a days we observe a lot of inter-sentential and intra-sentential code-mixing in songs which has a varying impact on audience. To study this impact we created a Telugu songs dataset which contained both Telugu-English code-mixed and pure Telugu songs. In this paper, we classify the songs based on its arousal as exciting or non-exciting. We develop a language identification tool and introduce code-mixing features obtained from it as additional features. Our system with these additional features attains 4-5% accuracy greater than traditional approaches on our dataset.
Tasks	Language Identification, Opinion Mining, Sentiment Analysis
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03821v1
PDF	http://arxiv.org/pdf/1806.03821v1.pdf
PWC	https://paperswithcode.com/paper/addition-of-code-mixed-features-to-enhance
Repo
Framework

Graph-based Hypothesis Generation for Parallax-tolerant Image Stitching


Title	Graph-based Hypothesis Generation for Parallax-tolerant Image Stitching
Authors	Jing Chen, Nan Li, Tianli Liao
Abstract	The seam-driven approach has been proven fairly effective for parallax-tolerant image stitching, whose strategy is to search for an invisible seam from finite representative hypotheses of local alignment. In this paper, we propose a graph-based hypothesis generation and a seam-guided local alignment for improving the effectiveness and the efficiency of the seam-driven approach. The experiment demonstrates the significant reduction of number of hypotheses and the improved quality of naturalness of final stitching results, comparing to the state-of-the-art method SEAGULL.
Tasks	Image Stitching
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07492v1
PDF	http://arxiv.org/pdf/1804.07492v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-hypothesis-generation-for
Repo
Framework

Grapevine: A Wine Prediction Algorithm Using Multi-dimensional Clustering Methods


Title	Grapevine: A Wine Prediction Algorithm Using Multi-dimensional Clustering Methods
Authors	Richard Diehl Martinez, Geoffrey Angus, Rooz Mahdavian
Abstract	We present a method for a wine recommendation system that employs multidimensional clustering and unsupervised learning methods. Our algorithm first performs clustering on a large corpus of wine reviews. It then uses the resulting wine clusters as an approximation of the most common flavor palates, recommending a user a wine by optimizing over a price-quality ratio within clusters that they demonstrated a preference for.
Tasks
Published	2018-06-29
URL	http://arxiv.org/abs/1807.00692v1
PDF	http://arxiv.org/pdf/1807.00692v1.pdf
PWC	https://paperswithcode.com/paper/grapevine-a-wine-prediction-algorithm-using
Repo
Framework

Detecting Volcano Deformation in InSAR using Deep learning


Title	Detecting Volcano Deformation in InSAR using Deep learning
Authors	N. Anantrasirichai, F. Albino, P. Hill, D. Bull, J. Biggs
Abstract	Globally 800 million people live within 100 km of a volcano and currently 1500 volcanoes are considered active, but half of these have no ground-based monitoring. Alternatively, satellite radar (InSAR) can be employed to observe volcanic ground deformation, which has shown a significant statistical link to eruptions. Modern satellites provide large coverage with high resolution signals, leading to huge amounts of data. The explosion in data has brought major challenges associated with timely dissemination of information and distinguishing volcano deformation patterns from noise, which currently relies on manual inspection. Moreover, volcano observatories still lack expertise to exploit satellite datasets, particularly in developing countries. This paper presents a novel approach to detect volcanic ground deformation automatically from wrapped-phase InSAR images. Convolutional neural networks (CNN) are employed to detect unusual patterns within the radar data.
Tasks
Published	2018-01-21
URL	http://arxiv.org/abs/1803.00380v1
PDF	http://arxiv.org/pdf/1803.00380v1.pdf
PWC	https://paperswithcode.com/paper/detecting-volcano-deformation-in-insar-using
Repo
Framework

2sRanking-CNN: A 2-stage ranking-CNN for diagnosis of glaucoma from fundus images using CAM-extracted ROI as an intermediate input


Title	2sRanking-CNN: A 2-stage ranking-CNN for diagnosis of glaucoma from fundus images using CAM-extracted ROI as an intermediate input
Authors	Tae Joon Jun, Dohyeun Kim, Hoang Minh Nguyen, Daeyoung Kim, Youngsub Eom
Abstract	Glaucoma is a disease in which the optic nerve is chronically damaged by the elevation of the intra-ocular pressure, resulting in visual field defect. Therefore, it is important to monitor and treat suspected patients before they are confirmed with glaucoma. In this paper, we propose a 2-stage ranking-CNN that classifies fundus images as normal, suspicious, and glaucoma. Furthermore, we propose a method of using the class activation map as a mask filter and combining it with the original fundus image as an intermediate input. Our results have improved the average accuracy by about 10% over the existing 3-class CNN and ranking-CNN, and especially improved the sensitivity of suspicious class by more than 20% over 3-class CNN. In addition, the extracted ROI was also found to overlap with the diagnostic criteria of the physician. The method we propose is expected to be efficiently applied to any medical data where there is a suspicious condition between normal and disease.
Tasks
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05727v2
PDF	http://arxiv.org/pdf/1805.05727v2.pdf
PWC	https://paperswithcode.com/paper/2sranking-cnn-a-2-stage-ranking-cnn-for
Repo
Framework

Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition


Title	Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition
Authors	Yunfeng Wang, Wengang Zhou, Qilin Zhang, Houqiang Li
Abstract	Visual attributes in individual video frames, such as the presence of characteristic objects and scenes, offer substantial information for action recognition in videos. With individual 2D video frame as input, visual attributes extraction could be achieved effectively and efficiently with more sophisticated convolutional neural network than current 3D CNNs with spatio-temporal filters, thanks to fewer parameters in 2D CNNs. In this paper, the integration of visual attributes (including detection, encoding and classification) into multi-stream 3D CNN is proposed for action recognition in trimmed videos, with the proposed visual Attribute-augmented 3D CNN (A3D) framework. The visual attribute pipeline includes an object detection network, an attributes encoding network and a classification network. Our proposed A3D framework achieves state-of-the-art performance on both the HMDB51 and the UCF101 datasets.
Tasks	Action Recognition In Videos, Object Detection, Temporal Action Localization
Published	2018-05-08
URL	http://arxiv.org/abs/1805.02860v1
PDF	http://arxiv.org/pdf/1805.02860v1.pdf
PWC	https://paperswithcode.com/paper/visual-attribute-augmented-three-dimensional
Repo
Framework