January 25, 2020

3352 words 16 mins read

Paper Group ANR 1682

LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks. A Comprehensive Performance Evaluation for 3D Transformation Estimation Techniques. Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks. Community-Level Anomaly Detection for Anti-Money Laundering. How is Your Mood When Writing Sexist tweets? …

LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks


Title	LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks
Authors	Jonathan Ephrath, Moshe Eliasof, Lars Ruthotto, Eldad Haber, Eran Treister
Abstract	Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network containing spatial convolution operators with compactly supported stencils. In practice, the input data and the hidden features consist of a large number of channels, which in most CNNs are fully coupled by the convolution operators. This coupling leads to immense computational cost in the training and prediction phase. In this paper, we introduce LeanConvNets that are derived by sparsifying fully-coupled operators in existing CNNs. Our goal is to improve the efficiency of CNNs by reducing the number of weights, floating point operations and latency times, with minimal loss of accuracy. Our lean convolution operators involve tuning parameters that controls the trade-off between the network’s accuracy and computational costs. These convolutions can be used in a wide range of existing networks, and we exemplify their use in residual networks (ResNets). Using a range of benchmark problems from image classification and semantic segmentation, we demonstrate that the resulting LeanConvNet’s accuracy is close to state-of-the-art networks while being computationally less expensive. In our tests, the lean versions of ResNet in most cases outperform comparable reduced architectures such as MobileNets and ShuffleNets.
Tasks	Image Classification, Semantic Segmentation, Speech Recognition
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13157v2
PDF	https://arxiv.org/pdf/1910.13157v2.pdf
PWC	https://paperswithcode.com/paper/leanconvnets-low-cost-yet-effective
Repo
Framework

A Comprehensive Performance Evaluation for 3D Transformation Estimation Techniques


Title	A Comprehensive Performance Evaluation for 3D Transformation Estimation Techniques
Authors	Bao Zhao, Xiaobo Chen, Xinyi Le, Juntong Xi
Abstract	3D local feature extraction and matching is the basis for solving many tasks in the area of computer vision, such as 3D registration, modeling, recognition and retrieval. However, this process commonly draws into false correspondences, due to noise, limited features, occlusion, incomplete surface and etc. In order to estimate accurate transformation based on these corrupted correspondences, numerous transformation estimation techniques have been proposed. However, the merits, demerits and appropriate application for these methods are unclear owing to that no comprehensive evaluation for the performance of these methods has been conducted. This paper evaluates eleven state-of-the-art transformation estimation proposals on both descriptor based and synthetic correspondences. On descriptor based correspondences, several evaluation items (including the performance on different datasets, robustness to different overlap ratios and the performance of these technique combined with Iterative Closest Point (ICP), different local features and LRF/A techniques) of these methods are tested on four popular datasets acquired with different devices. On synthetic correspondences, the robustness of these methods to varying percentages of correct correspondences (PCC) is evaluated. In addition, we also evaluate the efficiencies of these methods. Finally, the merits, demerits and application guidance of these tested transformation estimation methods are summarized.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05104v1
PDF	http://arxiv.org/pdf/1901.05104v1.pdf
PWC	https://paperswithcode.com/paper/a-comprehensive-performance-evaluation-for-3d
Repo
Framework

Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks


Title	Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks
Authors	Piotr S. Maciąg, Marzena Kryszkiewicz, Robert Bembenik, Jesus L. Lobo, Javier Del Ser
Abstract	In this work, we propose a novel OeSNN-UAD (Online evolving Spiking Neural Networks for Unsupervised Anomaly Detection) approach for online anomaly detection in univariate time series data. Our approach is based on evolving Spiking Neural Networks (eSNN). Its distinctive feature is that the proposed eSNN architecture learns in the process of classifying input values to be anomalous or not. In fact, we offer an unsupervised learning method for eSNN, in which classification is carried out without earlier pre-training of the network with data with labeled anomalies. Unlike in a typical eSNN architecture, neurons in the output repository of our architecture are not divided into known a priori decision classes. Each output neuron is assigned its own output value, which is modified in the course of learning and classifying the incoming input values of time series data. To better adapt to the changing characteristic of the input data and to make their classification efficient, the number of output neurons is limited: the older neurons are replaced with new neurons whose output values and synapses’ weights are adjusted according to the current input values of the time series. The proposed OeSNN-UAD approach was experimentally compared to the state-of-the-art unsupervised methods and algorithms for anomaly detection in stream data. The experiments were carried out on Numenta Anomaly Benchmark and Yahoo Anomaly Datasets. According to the results of these experiments, our approach significantly outperforms other solutions provided in the literature in the case of Numenta Anomaly Benchmark. Also in the case of real data files category of Yahoo Anomaly Benchmark, OeSNN-UAD outperforms other selected algorithms, whereas in the case of Yahoo Anomaly Benchmark synthetic data files, it provides competitive results to the results recently reported in the literature.
Tasks	Anomaly Detection, Time Series, Unsupervised Anomaly Detection
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08785v1
PDF	https://arxiv.org/pdf/1912.08785v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-anomaly-detection-in-stream-data
Repo
Framework

Community-Level Anomaly Detection for Anti-Money Laundering


Title	Community-Level Anomaly Detection for Anti-Money Laundering
Authors	Andra Baltoiu, Andrei Patrascu, Paul Irofti
Abstract	Anomaly detection in networks often boils down to identifying an underlying graph structure on which the abnormal occurrence rests on. Financial fraud schemes are one such example, where more or less intricate schemes are employed in order to elude transaction security protocols. We investigate the problem of learning graph structure representations using adaptations of dictionary learning aimed at encoding connectivity patterns. In particular, we adapt dictionary learning strategies to the specificity of network topologies and propose new methods that impose Laplacian structure on the dictionaries themselves. In one adaption we focus on classifying topologies by working directly on the graph Laplacian and cast the learning problem to accommodate its 2D structure. We tackle the same problem by learning dictionaries which consist of vectorized atomic Laplacians, and provide a block coordinate descent scheme to solve the new dictionary learning formulation. Imposing Laplacian structure on the dictionaries is also proposed in an adaptation of the Single Block Orthogonal learning method. Results on synthetic graph datasets comprising different graph topologies confirm the potential of dictionaries to directly represent graph structure information.
Tasks	Anomaly Detection, Dictionary Learning
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11313v1
PDF	https://arxiv.org/pdf/1910.11313v1.pdf
PWC	https://paperswithcode.com/paper/community-level-anomaly-detection-for-anti
Repo
Framework

How is Your Mood When Writing Sexist tweets? Detecting the Emotion Type and Intensity of Emotion Using Natural Language Processing Techniques


Title	How is Your Mood When Writing Sexist tweets? Detecting the Emotion Type and Intensity of Emotion Using Natural Language Processing Techniques
Authors	Sima Sharifirad, Borna Jafarpour, Stan Matwin
Abstract	Online social platforms have been the battlefield of users with different emotions and attitudes toward each other in recent years. While sexism has been considered as a category of hateful speech in the literature, there is no comprehensive definition and category of sexism attracting natural language processing techniques. Categorizing sexism as either benevolent or hostile sexism is so broad that it easily ignores the other categories of sexism on social media. Sharifirad S and Matwin S 2018 proposed a well-defined category of sexism including indirect harassment, information threat, sexual harassment and physical harassment, inspired from social science for the purpose of natural language processing techniques. In this article, we take advantage of a newly released dataset in SemEval-2018 task1: Affect in tweets, to show the type of emotion and intensity of emotion in each category. We train, test and evaluate different classification methods on the SemEval- 2018 dataset and choose the classifier with highest accuracy for testing on each category of sexist tweets to know the mental state and the affectual state of the user who tweets in each category. It is a nice avenue to explore because not all the tweets are directly sexist and they carry different emotions from the users. This is the first work experimenting on affect detection this in depth on sexist tweets. Based on our best knowledge they are all new contributions to the field; we are the first to demonstrate the power of such in-depth sentiment analysis on the sexist tweets.
Tasks	Sentiment Analysis
Published	2019-01-28
URL	http://arxiv.org/abs/1902.03089v1
PDF	http://arxiv.org/pdf/1902.03089v1.pdf
PWC	https://paperswithcode.com/paper/how-is-your-mood-when-writing-sexist-tweets
Repo
Framework

Dictionary Learning with Almost Sure Error Constraints


Title	Dictionary Learning with Almost Sure Error Constraints
Authors	Mohammed Rayyan Sheriff, Debasish Chatterjee
Abstract	A dictionary is a database of standard vectors, so that other vectors / signals are expressed as linear combinations of dictionary vectors, and the task of learning a dictionary for a given data is to find a good dictionary so that the representation of data points has desirable features. Dictionary learning and the related matrix factorization methods have gained significant prominence recently due to their applications in Wide variety of fields like machine learning, signal processing, statistics etc. In this article we study the dictionary learning problem for achieving desirable features in the representation of a given data with almost sure recovery constraints. We impose the constraint that every sample is reconstructed properly to within a predefined threshold. This problem formulation is more challenging than the conventional dictionary learning, which is done by minimizing a regularised cost function. We make use of the duality results for linear inverse problems to obtain an equivalent reformulation in the form of a convex-concave min-max problem. The resulting min-max problem is then solved using gradient descent-ascent like algorithms.
Tasks	Dictionary Learning
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08828v2
PDF	https://arxiv.org/pdf/1910.08828v2.pdf
PWC	https://paperswithcode.com/paper/dictionary-learning-with-almost-sure-error
Repo
Framework

Towards Improving Generalization of Deep Networks via Consistent Normalization


Title	Towards Improving Generalization of Deep Networks via Consistent Normalization
Authors	Aojun Zhou, Yukun Ma, Yudian Li, Xiaohan Zhang, Ping Luo
Abstract	Batch Normalization (BN) was shown to accelerate training and improve generalization of Convolutional Neural Networks (ConvNets), which typically use the Conv-BN couple as building block. However, this work shows a common phenomenon that the Conv-BN module does not necessarily outperform the networks trained without using BN, especially when data augmentation is presented in training. We find that this phenomenon occurs because there is inconsistency between the distribution of the augmented data and that of the normalized representation. To address this issue, we propose Consistent Normalization (CN) that not only retains the advantages of the existing normalization methods, but also achieves state-of-the-art performance on various tasks including image classification, segmentation, and machine translation. The code will be released to facilitate reproducibility.
Tasks	Data Augmentation, Image Classification, Machine Translation
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00182v1
PDF	https://arxiv.org/pdf/1909.00182v1.pdf
PWC	https://paperswithcode.com/paper/towards-improving-generalization-of-deep
Repo
Framework

Learning Objectness from Sonar Images for Class-Independent Object Detection


Title	Learning Objectness from Sonar Images for Class-Independent Object Detection
Authors	Matias Valdenegro-Toro
Abstract	Detecting novel objects without class information is not trivial, as it is difficult to generalize from a small training set. This is an interesting problem for underwater robotics, as modeling marine objects is inherently more difficult in sonar images, and training data might not be available apriori. Detection proposals algorithms can be used for this purpose but usually requires a large amount of output bounding boxes. In this paper we propose the use of a fully convolutional neural network that regresses an objectness value directly from a Forward-Looking sonar image. By ranking objectness, we can produce high recall (96 %) with only 100 proposals per image. In comparison, EdgeBoxes requires 5000 proposals to achieve a slightly better recall of 97 %, while Selective Search requires 2000 proposals to achieve 95 % recall. We also show that our method outperforms a template matching baseline by a considerable margin, and is able to generalize to completely new objects. We expect that this kind of technique can be used in the field to find lost objects under the sea.
Tasks	Object Detection
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00734v1
PDF	https://arxiv.org/pdf/1907.00734v1.pdf
PWC	https://paperswithcode.com/paper/learning-objectness-from-sonar-images-for
Repo
Framework

A Tree-based Dictionary Learning Framework


Title	A Tree-based Dictionary Learning Framework
Authors	Renato Budinich, Gerlind Plonka
Abstract	We propose a new outline for dictionary learning methods based on a hierarchical clustering of the training data. Through recursive application of a clustering method the data is organized into a binary partition tree representing a multiscale structure. The dictionary atoms are defined adaptively based on the data clusters in the partition tree. This approach can be interpreted as a generalization of the wavelet transform. The computational bottleneck of the procedure is then the chosen clustering method: when using K-means the method runs much faster than K-SVD. Thanks to the multiscale properties of the partition tree, our dictionary is structured: when using Orthogonal Matching Pursuit to reconstruct patches from a natural image, dictionary atoms corresponding to nodes being closer to the root node in the tree have a tendency to be used with greater coefficients.
Tasks	Dictionary Learning
Published	2019-09-07
URL	https://arxiv.org/abs/1909.03267v1
PDF	https://arxiv.org/pdf/1909.03267v1.pdf
PWC	https://paperswithcode.com/paper/a-tree-based-dictionary-learning-framework
Repo
Framework

A regression algorithm for accelerated lattice QCD that exploits sparse inference on the D-Wave quantum annealer


Title	A regression algorithm for accelerated lattice QCD that exploits sparse inference on the D-Wave quantum annealer
Authors	Nga T. T. Nguyen, Garrett T. Kenyon, Boram Yoon
Abstract	We propose a regression algorithm that utilizes a learned dictionary optimized for sparse inference on D-Wave quantum annealer. In this regression algorithm, we concatenate the independent and dependent variables as an combined vector, and encode the high-order correlations between them into a dictionary optimized for sparse reconstruction. On a test dataset, the dependent variable is initialized to its average value and then a sparse reconstruction of the combined vector is obtained in which the dependent variable is typically shifted closer to its true value, as in a standard inpainting or denoising task. Here, a quantum annealer, which can presumably exploit a fully entangled initial state to better explore the complex energy landscape, is used to solve the highly non-convex sparse coding optimization problem. The regression algorithm is demonstrated for a lattice quantum chromodynamics simulation data using a D-Wave 2000Q quantum annealer and good prediction performance is achieved. The regression test is performed using six different values for the number of fully connected logical qubits, between 20 and 64, the latter being the maximum that can be embedded on the D-Wave 2000Q. The scaling results indicate that a larger number of qubits gives better prediction accuracy, the best performance being comparable to the best classical regression algorithms reported so far.
Tasks	Denoising
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06267v1
PDF	https://arxiv.org/pdf/1911.06267v1.pdf
PWC	https://paperswithcode.com/paper/a-regression-algorithm-for-accelerated
Repo
Framework

Recurrent Adversarial Service Times


Title	Recurrent Adversarial Service Times
Authors	César Ojeda, Kostadin Cvejosky, Ramsés J. Sánchez, Jannis Schuecker, Bogdan Georgiev, Christian Bauckhage
Abstract	Service system dynamics occur at the interplay between customer behaviour and a service provider’s response. This kind of dynamics can effectively be modeled within the framework of queuing theory where customers’ arrivals are described by point process models. However, these approaches are limited by parametric assumptions as to, for example, inter-event time distributions. In this paper, we address these limitations and propose a novel, deep neural network solution to the queuing problem. Our solution combines a recurrent neural network that models the arrival process with a recurrent generative adversarial network which models the service time distribution. We evaluate our methodology on various empirical datasets ranging from internet services (Blockchain, GitHub, Stackoverflow) to mobility service systems (New York taxi cab).
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09808v1
PDF	https://arxiv.org/pdf/1906.09808v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-adversarial-service-times
Repo
Framework

Hierarchical Recurrent Neural Network for Video Summarization


Title	Hierarchical Recurrent Neural Network for Video Summarization
Authors	Bin Zhao, Xuelong Li, Xiaoqiang Lu
Abstract	Exploiting the temporal dependency among video frames or subshots is very important for the task of video summarization. Practically, RNN is good at temporal dependency modeling, and has achieved overwhelming performance in many video-based tasks, such as video captioning and classification. However, RNN is not capable enough to handle the video summarization task, since traditional RNNs, including LSTM, can only deal with short videos, while the videos in the summarization task are usually in longer duration. To address this problem, we propose a hierarchical recurrent neural network for video summarization, called H-RNN in this paper. Specifically, it has two layers, where the first layer is utilized to encode short video subshots cut from the original video, and the final hidden state of each subshot is input to the second layer for calculating its confidence to be a key subshot. Compared to traditional RNNs, H-RNN is more suitable to video summarization, since it can exploit long temporal dependency among frames, meanwhile, the computation operations are significantly lessened. The results on two popular datasets, including the Combined dataset and VTW dataset, have demonstrated that the proposed H-RNN outperforms the state-of-the-arts.
Tasks	Video Captioning, Video Summarization
Published	2019-04-28
URL	http://arxiv.org/abs/1904.12251v1
PDF	http://arxiv.org/pdf/1904.12251v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-recurrent-neural-network-for-2
Repo
Framework

Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music


Title	Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music
Authors	Hyemin Ahn, Jaehun Kim, Kihyun Kim, Songhwai Oh
Abstract	This paper proposes a framework which is able to generate a sequence of three-dimensional human dance poses for a given music. The proposed framework consists of three components: a music feature encoder, a pose generator, and a music genre classifier. We focus on integrating these components for generating a realistic 3D human dancing move from music, which can be applied to artificial agents and humanoid robots. The trained dance pose generator, which is a generative autoregressive model, is able to synthesize a dance sequence longer than 5,000 pose frames. Experimental results of generated dance sequences from various songs show how the proposed method generates human-like dancing move to a given music. In addition, a generated 3D dance sequence is applied to a humanoid robot, showing that the proposed framework can make a robot to dance just by listening to music.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04069v1
PDF	https://arxiv.org/pdf/1911.04069v1.pdf
PWC	https://paperswithcode.com/paper/generative-autoregressive-networks-for-3d
Repo
Framework

A Physical Testbed for Intelligent Transportation Systems


Title	A Physical Testbed for Intelligent Transportation Systems
Authors	Adam Morrissett, Roja Eini, Mostafa Zaman, Nasibeh Zohrabi, Sherif Abdelwahed
Abstract	Intelligent transportation systems (ITSs) and other smart-city technologies are increasingly advancing in capability and complexity. While simulation environments continue to improve, their fidelity and ease of use can quickly degrade as newer systems become increasingly complex. To remedy this, we propose a hardware- and software-based traffic management system testbed as part of a larger smart-city testbed. It comprises a network of connected vehicles, a network of intersection controllers, a variety of control services, and data analytics services. The main goal of our testbed is to provide researchers and students with the means to develop novel traffic and vehicle control algorithms with higher fidelity than what can be achieved with simulation alone. Specifically, we are using the testbed to develop an integrated management system that combines model-based control and data analytics to improve the system performance over time. In this paper, we give a detailed description of each component within the testbed and discuss its current developmental state. Additionally, we present initial results and propose future work. Index Terms: Smart city, Intelligent transportation systems, Human-in-the-loop, Data analytics, Data visualization, Traffic network management and control, Machine learning.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.12899v1
PDF	https://arxiv.org/pdf/1907.12899v1.pdf
PWC	https://paperswithcode.com/paper/a-physical-testbed-for-intelligent
Repo
Framework

Realizing data features by deep nets


Title	Realizing data features by deep nets
Authors	Zheng-Chu Guo, Lei Shi, Shao-Bo Lin
Abstract	This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additional capacity costs. This verifies the advantage of deep nets in realizing complex features. On the other hand, to realize some simple data feature like the smoothness, we prove that, up to a logarithmic factor, the approximation rate of deep nets is asymptotically identical to that of shallow nets, provided that the depth is fixed. This exhibits a limitation of deep nets in realizing simple features.
Tasks
Published	2019-01-01
URL	http://arxiv.org/abs/1901.00130v1
PDF	http://arxiv.org/pdf/1901.00130v1.pdf
PWC	https://paperswithcode.com/paper/realizing-data-features-by-deep-nets
Repo
Framework