April 2, 2020

3037 words 15 mins read

Paper Group ANR 280

An IoT-Based System: Big Urban Traffic Data Mining Through Airborne Pollutant Gases Analysis. Cross-layer Feature Pyramid Network for Salient Object Detection. Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread. ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network Architectures. Searching …

An IoT-Based System: Big Urban Traffic Data Mining Through Airborne Pollutant Gases Analysis


Title	An IoT-Based System: Big Urban Traffic Data Mining Through Airborne Pollutant Gases Analysis
Authors	Daniel. Firouzimagham, Mohammad. Sabouri, Fatemeh. Adhami
Abstract	Nowadays, in developing countries including Iran, the number of vehicles is increasing due to growing population. This has recently led to waste time getting stuck in traffic, take more time for daily commute, and increase accidents. So it is necessary to control traffic congestion by traffic police officers, expand paths efficiently and choose the best way for decreasing the traffic by citizens. Therefore, it is important to have the knowledge of instant traffic in each lane. Todays, many traffic organization services such as traffic police officer and urban traffic control system use traffic cameras, inductive sensors, satellite images, radar sensors, ultrasonic technology and radio-frequency identification (RFID) for urban traffic diagnosis. But this method has some problems such as inefficiency in heavy traffic influenced by condition of the air and inability to detect parallel traffic. Our method suggested in this article detects traffic congestion based on IOT containing a smart system that gives us traffic congestion by calculating the air pollution amount in that area. According to conducted experiment, the results were satisfied.
Tasks
Published	2020-02-15
URL	https://arxiv.org/abs/2002.06374v1
PDF	https://arxiv.org/pdf/2002.06374v1.pdf
PWC	https://paperswithcode.com/paper/an-iot-based-system-big-urban-traffic-data
Repo
Framework

Cross-layer Feature Pyramid Network for Salient Object Detection


Title	Cross-layer Feature Pyramid Network for Salient Object Detection
Authors	Zun Li, Congyan Lang, Junhao Liew, Qibin Hou, Yidong Li, Jiashi Feng
Abstract	Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection. However, it is observed that these models often generate saliency maps with incomplete object structures or unclear object boundaries, due to the \emph{indirect} information propagation among distant layers that makes such fusion structure less effective. In this work, we propose a novel Cross-layer Feature Pyramid Network (CFPN), in which direct cross-layer communication is enabled to improve the progressive fusion in salient object detection. Specifically, the proposed network first aggregates multi-scale features from different layers into feature maps that have access to both the high- and low-level information. Then, it distributes the aggregated features to all the involved layers to gain access to richer context. In this way, the distributed features per layer own both semantics and salient details from all other layers simultaneously, and suffer reduced loss of important information. Extensive experimental results over six widely used salient object detection benchmarks and with three popular backbones clearly demonstrate that CFPN can accurately locate fairly complete salient regions and effectively segment the object boundaries.
Tasks	Object Detection, Salient Object Detection
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10864v1
PDF	https://arxiv.org/pdf/2002.10864v1.pdf
PWC	https://paperswithcode.com/paper/cross-layer-feature-pyramid-network-for
Repo
Framework

Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread


Title	Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
Authors	Haofeng Li, Guanbin Li, Binbin Yang, Guanqi Chen, Liang Lin, Yizhou Yu
Abstract	Recently deep convolutional neural networks have achieved significant success in salient object detection. However, existing state-of-the-art methods require high-end GPUs to achieve real-time performance, which makes them hard to adapt to low-cost or portable devices. Although generic network architectures have been proposed to speed up inference on mobile devices, they are tailored to the task of image classification or semantic segmentation, and struggle to capture intra-channel and inter-channel correlations that are essential for contrast modeling in salient object detection. Motivated by the above observations, we design a new deep learning algorithm for fast salient object detection. The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread. Specifically, we propose a novel depthwise non-local moudule (DNL), which implicitly models contrast via harvesting intra-channel and inter-channel correlations in a self-attention manner. In addition, we introduce a depthwise non-local network architecture that incorporates both depthwise non-local modules and inverted residual blocks. Experimental results show that our proposed network attains very competitive accuracy on a wide range of salient object detection datasets while achieving state-of-the-art efficiency among all existing deep learning based algorithms.
Tasks	Image Classification, Object Detection, Salient Object Detection, Semantic Segmentation
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08057v1
PDF	https://arxiv.org/pdf/2001.08057v1.pdf
PWC	https://paperswithcode.com/paper/depthwise-non-local-module-for-fast-salient
Repo
Framework

ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network Architectures


Title	ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network Architectures
Authors	Kefan Chen, Wei Pang
Abstract	In this research, we propose ImmuNetNAS, a novel Neural Architecture Search (NAS) approach inspired by the immune network theory. The core of ImmuNetNAS is built on the original immune network algorithm, which iteratively updates the population through hypermutation and selection, and eliminates the self-generation individuals that do not meet the requirements through comparing antibody affinity and inter-specific similarity. In addition, in order to facilitate the mutation operation, we propose a novel two-component based neural structure coding strategy. Furthermore, an improved mutation strategy based on Standard Genetic Algorithm (SGA) was proposed according to this encoding method. Finally, based on the proposed two-component based coding method, a new antibody affinity calculation method was developed to screen suitable neural architectures. Systematic evaluations demonstrate that our system has achieved good performance on both the MNIST and CIFAR-10 datasets. We open-source our code on GitHub in order to share it with other deep learning researchers and practitioners.
Tasks	Neural Architecture Search
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12704v1
PDF	https://arxiv.org/pdf/2002.12704v1.pdf
PWC	https://paperswithcode.com/paper/immunetnas-an-immune-network-approach-for
Repo
Framework

Searching for Winograd-aware Quantized Networks


Title	Searching for Winograd-aware Quantized Networks
Authors	Javier Fernandez-Marques, Paul N. Whatmough, Andrew Mundy, Matthew Mattina
Abstract	Lightweight architectural designs of Convolutional Neural Networks (CNNs) together with quantization have paved the way for the deployment of demanding computer vision applications on mobile devices. Parallel to this, alternative formulations to the convolution operation such as FFT, Strassen and Winograd, have been adapted for use in CNNs offering further speedups. Winograd convolutions are the fastest known algorithm for spatially small convolutions, but exploiting their full potential comes with the burden of numerical error, rendering them unusable in quantized contexts. In this work we propose a Winograd-aware formulation of convolution layers which exposes the numerical inaccuracies introduced by the Winograd transformations to the learning of the model parameters, enabling the design of competitive quantized models without impacting model size. We also address the source of the numerical error and propose a relaxation on the form of the transformation matrices, resulting in up to 10% higher classification accuracy on CIFAR-10. Finally, we propose wiNAS, a neural architecture search (NAS) framework that jointly optimizes a given macro-architecture for accuracy and latency leveraging Winograd-aware layers. A Winograd-aware ResNet-18 optimized with wiNAS for CIFAR-10 results in 2.66x speedup compared to im2row, one of the most widely used optimized convolution implementations, with no loss in accuracy.
Tasks	Neural Architecture Search, Quantization
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10711v1
PDF	https://arxiv.org/pdf/2002.10711v1.pdf
PWC	https://paperswithcode.com/paper/searching-for-winograd-aware-quantized
Repo
Framework

EmbPred30: Assessing 30-days Readmission for Diabetic Patients using Categorical Embeddings


Title	EmbPred30: Assessing 30-days Readmission for Diabetic Patients using Categorical Embeddings
Authors	Sarthak, Shikhar Shukla, Surya Prakash Tripathi
Abstract	Hospital readmission is a crucial healthcare quality measure that helps in determining the level of quality of care that a hospital offers to a patient and has proven to be immensely expensive. It is estimated that more than $25 billion are spent yearly due to readmission of diabetic patients in the USA. This paper benchmarks existing models and proposes a new embedding based state-of-the-art deep neural network(DNN). The model can identify whether a hospitalized diabetic patient will be readmitted within 30 days or not with an accuracy of 95.2% and Area Under the Receiver Operating Characteristics(AUROC) of 97.4% on data collected from 130 US hospitals between 1999-2008. The results are encouraging with patients having changes in medication while admitted having a high chance of getting readmitted. Identifying prospective patients for readmission could help the hospital systems in improving their inpatient care, thereby saving them from unnecessary expenditures.
Tasks
Published	2020-02-25
URL	https://arxiv.org/abs/2002.11215v1
PDF	https://arxiv.org/pdf/2002.11215v1.pdf
PWC	https://paperswithcode.com/paper/embpred30-assessing-30-days-readmission-for
Repo
Framework

Machine learning in quantum computers via general Boltzmann Machines: Generative and Discriminative training through annealing


Title	Machine learning in quantum computers via general Boltzmann Machines: Generative and Discriminative training through annealing
Authors	Siddhartha Srivastava, Veera Sundararaghavan
Abstract	We present a Hybrid-Quantum-classical method for learning Boltzmann machines (BM) for generative and discriminative tasks. Boltzmann machines are undirected graphs that form the building block of many learning architectures such as Restricted Boltzmann machines (RBM’s) and Deep Boltzmann machines (DBM’s). They have a network of visible and hidden nodes where the former are used as the reading sites while the latter are used to manipulate the probability of the visible states. BM’s are versatile machines that can be used for both learning distributions as a generative task as well as for performing classification or function approximation as a discriminative task. We show that minimizing KL-divergence works best for training BM for applications of function approximation. In our approach, we use Quantum annealers for sampling Boltzmann states. These states are used to approximate gradients in a stochastic gradient descent scheme. The approach is used to demonstrate logic circuits in the discriminative sense and a specialized two-phase distribution using generative BM.
Tasks
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00792v2
PDF	https://arxiv.org/pdf/2002.00792v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-in-quantum-computers-via
Repo
Framework

Wasserstein Proximal Gradient


Title	Wasserstein Proximal Gradient
Authors	Adil Salim, Anna Korba, Giulia Luise
Abstract	We consider the task of sampling from a log-concave probability distribution. This target distribution can be seen as a minimizer of the relative entropy functional defined on the space of probability distributions. The relative entropy can be decomposed as the sum of a functional called the potential energy, assumed to be smooth, and a nonsmooth functional called the entropy. We adopt a Forward Backward (FB) Euler scheme for the discretization of the gradient flow of the relative entropy. This FB algorithm can be seen as a proximal gradient algorithm to minimize the relative entropy over the space of probability measures. Using techniques from convex optimization and optimal transport, we provide a non-asymptotic analysis of the FB algorithm. The convergence rate of the FB algorithm matches the convergence rate of the classical proximal gradient algorithm in Euclidean spaces. The practical implementation of the FB algorithm can be challenging. In practice, the user may choose to discretize the space and work with empirical measures. In this case, we provide a closed form formula for the proximity operator of the entropy.
Tasks
Published	2020-02-07
URL	https://arxiv.org/abs/2002.03035v1
PDF	https://arxiv.org/pdf/2002.03035v1.pdf
PWC	https://paperswithcode.com/paper/wasserstein-proximal-gradient
Repo
Framework

Multi-Sensor Data and Knowledge Fusion – A Proposal for a Terminology Definition


Title	Multi-Sensor Data and Knowledge Fusion – A Proposal for a Terminology Definition
Authors	Silvia Beddar-Wiesing, Maarten Bieshaar
Abstract	Fusion is a common tool for the analysis and utilization of available datasets and so an essential part of data mining and machine learning processes. However, a clear definition of the type of fusion is not always provided due to inconsistent literature. In the following, the process of fusion is defined depending on the fusion components and the abstraction level on which the fusion occurs. The focus in the first part of the paper at hand is on the clear definition of the terminology and the development of an appropriate ontology of the fusion components and the fusion level. In the second part, common fusion techniques are presented.
Tasks
Published	2020-01-13
URL	https://arxiv.org/abs/2001.04171v1
PDF	https://arxiv.org/pdf/2001.04171v1.pdf
PWC	https://paperswithcode.com/paper/multi-sensor-data-and-knowledge-fusion-a
Repo
Framework

Moving Objects Detection with a Moving Camera: A Comprehensive Review


Title	Moving Objects Detection with a Moving Camera: A Comprehensive Review
Authors	Marie-Neige Chapel, Thierry Bouwmans
Abstract	During about 30 years, a lot of research teams have worked on the big challenge of detection of moving objects in various challenging environments. First applications concern static cameras but with the rise of the mobile sensors studies on moving cameras have emerged over time. In this survey, we propose to identify and categorize the different existing methods found in the literature. For this purpose, we propose to classify these methods according to the choose of the scene representation: one plane or several parts. Inside these two categories, the methods are grouped according to eight different approaches: panoramic background subtraction, dual cameras, motion compensation, subspace segmentation, motion segmentation, plane+parallax, multi planes and split image in blocks. A reminder of methods for static cameras is provided as well as the challenges with both static and moving cameras. Publicly available datasets and evaluation metrics are also surveyed in this paper.
Tasks	Motion Compensation, Motion Segmentation
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05238v1
PDF	https://arxiv.org/pdf/2001.05238v1.pdf
PWC	https://paperswithcode.com/paper/moving-objects-detection-with-a-moving-camera
Repo
Framework

Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G


Title	Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G
Authors	Rui Dong, Changyang She, Wibowo Hardjawana, Yonghui Li, Branka Vucetic
Abstract	To accommodate diverse Quality-of-Service (QoS) requirements in the 5th generation cellular networks, base stations need real-time optimization of radio resources in time-varying network conditions. This brings high computing overheads and long processing delays. In this work, we develop a deep learning framework to approximate the optimal resource allocation policy that minimizes the total power consumption of a base station by optimizing bandwidth and transmit power allocation. We find that a fully-connected neural network (NN) cannot fully guarantee the QoS requirements due to the approximation errors and quantization errors of the numbers of subcarriers. To tackle this problem, we propose a cascaded structure of NNs, where the first NN approximates the optimal bandwidth allocation, and the second NN outputs the transmit power required to satisfy the QoS requirement with given bandwidth allocation. Considering that the distribution of wireless channels and the types of services in the wireless networks are non-stationary, we apply deep transfer learning to update NNs in non-stationary wireless networks. Simulation results validate that the cascaded NNs outperform the fully connected NN in terms of QoS guarantee. In addition, deep transfer learning can reduce the number of training samples required to train the NNs remarkably.
Tasks	Quantization, Transfer Learning
Published	2020-03-29
URL	https://arxiv.org/abs/2004.00507v1
PDF	https://arxiv.org/pdf/2004.00507v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-radio-resource-allocation-1
Repo
Framework

Interpretable Deep Learning Model for Online Multi-touch Attribution


Title	Interpretable Deep Learning Model for Online Multi-touch Attribution
Authors	Dongdong Yang, Kevin Dyer, Senzhang Wang
Abstract	In online advertising, users may be exposed to a range of different advertising campaigns, such as natural search or referral or organic search, before leading to a final transaction. Estimating the contribution of advertising campaigns on the user’s journey is very meaningful and crucial. A marketer could observe each customer’s interaction with different marketing channels and modify their investment strategies accordingly. Existing methods including both traditional last-clicking methods and recent data-driven approaches for the multi-touch attribution (MTA) problem lack enough interpretation on why the methods work. In this paper, we propose a novel model called DeepMTA, which combines deep learning model and additive feature explanation model for interpretable online multi-touch attribution. DeepMTA mainly contains two parts, the phased-LSTMs based conversion prediction model to catch different time intervals, and the additive feature attribution model combined with shaley values. Additive feature attribution is explanatory that contains a linear function of binary variables. As the first interpretable deep learning model for MTA, DeepMTA considers three important features in the customer journey: event sequence order, event frequency and time-decay effect of the event. Evaluation on a real dataset shows the proposed conversion prediction model achieves 91% accuracy.
Tasks
Published	2020-03-26
URL	https://arxiv.org/abs/2004.00384v1
PDF	https://arxiv.org/pdf/2004.00384v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-deep-learning-model-for-online
Repo
Framework

Population-based metaheuristics for Association Rule Text Mining


Title	Population-based metaheuristics for Association Rule Text Mining
Authors	Iztok Fister Jr., Suash Deb, Iztok Fister
Abstract	Nowadays, the majority of data on the Internet is held in an unstructured format, like websites and e-mails. The importance of analyzing these data has been growing day by day. Similar to data mining on structured data, text mining methods for handling unstructured data have also received increasing attention from the research community. The paper deals with the problem of Association Rule Text Mining. To solve the problem, the PSO-ARTM method was proposed, that consists of three steps: Text preprocessing, Association Rule Text Mining using population-based metaheuristics, and text postprocessing. The method was applied to a transaction database obtained from professional triathlon athletes’ blogs and news posted on their websites. The obtained results reveal that the proposed method is suitable for Association Rule Text Mining and, therefore, offers a promising way for further development.
Tasks
Published	2020-01-17
URL	https://arxiv.org/abs/2001.06517v1
PDF	https://arxiv.org/pdf/2001.06517v1.pdf
PWC	https://paperswithcode.com/paper/population-based-metaheuristics-for
Repo
Framework

Group Membership Verification with Privacy: Sparse or Dense?


Title	Group Membership Verification with Privacy: Sparse or Dense?
Authors	Marzieh Gheisari, Teddy Furon, Laurent Amsaleg
Abstract	Group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member. Recent contributions provide privacy for group membership protocols through the joint use of two mechanisms: quantizing templates into discrete embeddings and aggregating several templates into one group representation. However, this scheme has one drawback: the data structure representing the group has a limited size and cannot recognize noisy queries when many templates are aggregated. Moreover, the sparsity of the embeddings seemingly plays a crucial role on the performance verification. This paper proposes a mathematical model for group membership verification allowing to reveal the impact of sparsity on both security, compactness, and verification performances. This model bridges the gap towards a Bloom filter robust to noisy queries. It shows that a dense solution is more competitive unless the queries are almost noiseless.
Tasks
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10362v1
PDF	https://arxiv.org/pdf/2002.10362v1.pdf
PWC	https://paperswithcode.com/paper/group-membership-verification-with-privacy
Repo
Framework

Understanding the dynamics of message passing algorithms: a free probability heuristics


Title	Understanding the dynamics of message passing algorithms: a free probability heuristics
Authors	Manfred Opper, Burak Çakmak
Abstract	We use freeness assumptions of random matrix theory to analyze the dynamical behavior of inference algorithms for probabilistic models with dense coupling matrices in the limit of large systems. For a toy Ising model, we are able to recover previous results such as the property of vanishing effective memories and the analytical convergence rate of the algorithm.
Tasks
Published	2020-02-03
URL	https://arxiv.org/abs/2002.02533v1
PDF	https://arxiv.org/pdf/2002.02533v1.pdf
PWC	https://paperswithcode.com/paper/understanding-the-dynamics-of-message-passing
Repo
Framework