Paper Group ANR 1214
Semantic Analysis of Traffic Camera Data: Topic Signal Extraction and Anomalous Event Detection. Short-and-Sparse Deconvolution – A Geometric Approach. Blind Image Deconvolution using Pretrained Generative Priors. An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration. Edge Heuristic GAN for Non-uniform Blind Deblu …
Semantic Analysis of Traffic Camera Data: Topic Signal Extraction and Anomalous Event Detection
| Title | Semantic Analysis of Traffic Camera Data: Topic Signal Extraction and Anomalous Event Detection |
| Authors | Jeffrey Liu, Andrew Weinert, Saurabh Amin |
| Abstract | Traffic Management Centers (TMCs) routinely use traffic cameras to provide situational awareness regarding traffic, road, and weather conditions. Camera footage is quite useful for a variety of diagnostic purposes; yet, most footage is kept for only a few days, if at all. This is largely due to the fact that currently, identification of notable footage is done via manual review by human operators—a laborious and inefficient process. In this article, we propose a semantics-oriented approach to analyzing sequential image data, and demonstrate its application for automatic detection of real-world, anomalous events in weather and traffic conditions. Our approach constructs semantic vector representations of image contents from textual labels which can be easily obtained from off-the-shelf, pretrained image labeling software. These semantic label vectors are used to construct semantic topic signals—time series representations of physical processes—using the Latent Dirichlet Allocation (LDA) topic model. By detecting anomalies in the topic signals, we identify notable footage corresponding to winter storms and anomalous traffic congestion. In validation against real-world events, anomaly detection using semantic topic signals significantly outperforms detection using any individual label signal. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07332v1 |
| https://arxiv.org/pdf/1905.07332v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-analysis-of-traffic-camera-data |
| Repo | |
| Framework | |
Short-and-Sparse Deconvolution – A Geometric Approach
| Title | Short-and-Sparse Deconvolution – A Geometric Approach |
| Authors | Yenson Lau, Qing Qu, Han-Wen Kuo, Pengcheng Zhou, Yuqian Zhang, John Wright |
| Abstract | Short-and-sparse deconvolution (SaSD) is the problem of extracting localized, recurring motifs in signals with spatial or temporal structure. Variants of this problem arise in applications such as image deblurring, microscopy, neural spike sorting, and more. The problem is challenging in both theory and practice, as natural optimization formulations are nonconvex. Moreover, practical deconvolution problems involve smooth motifs (kernels) whose spectra decay rapidly, resulting in poor conditioning and numerical challenges. This paper is motivated by recent theoretical advances, which characterize the optimization landscape of a particular nonconvex formulation of SaSD. This is used to derive a $provable$ algorithm which exactly solves certain non-practical instances of the SaSD problem. We leverage the key ideas from this theory (sphere constraints, data-driven initialization) to develop a $practical$ algorithm, which performs well on data arising from a range of application areas. We highlight key additional challenges posed by the ill-conditioning of real SaSD problems, and suggest heuristics (acceleration, continuation, reweighting) to mitigate them. Experiments demonstrate both the performance and generality of the proposed method. |
| Tasks | Deblurring |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10959v2 |
| https://arxiv.org/pdf/1908.10959v2.pdf | |
| PWC | https://paperswithcode.com/paper/short-and-sparse-deconvolution-a-geometric |
| Repo | |
| Framework | |
Blind Image Deconvolution using Pretrained Generative Priors
| Title | Blind Image Deconvolution using Pretrained Generative Priors |
| Authors | Muhammad Asim, Fahad Shamshad, Ali Ahmed |
| Abstract | This paper proposes a novel approach to regularize the ill-posed blind image deconvolution (blind image deblurring) problem using deep generative networks. We employ two separate deep generative models - one trained to produce sharp images while the other trained to generate blur kernels from lower dimensional parameters. To deblur, we propose an alternating gradient descent scheme operating in the latent lower-dimensional space of each of the pretrained generative models. Our experiments show excellent deblurring results even under large blurs and heavy noise. To improve the performance on rich image datasets not well learned by the generative networks, we present a modification of the proposed scheme that governs the deblurring process under both generative and classical priors. |
| Tasks | Blind Image Deblurring, Deblurring, Image Deconvolution |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07404v1 |
| https://arxiv.org/pdf/1908.07404v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-image-deconvolution-using-pretrained |
| Repo | |
| Framework | |
An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration
| Title | An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration |
| Authors | Alexander Effland, Erich Kobler, Karl Kunisch, Thomas Pock |
| Abstract | We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point. This paradox originates from a tradeoff between optimization and modelling errors of the underlying variational model and holds true even if deep learning methods are used to learn highly expressive regularizers from data. In this paper, we take advantage of this paradox and introduce an optimal stopping time into the gradient flow process, which in turn is learned from data by means of an optimal control approach. As a result, we obtain highly efficient numerical schemes that achieve competitive results for image denoising and image deblurring. A nonlinear spectral analysis of the gradient of the learned regularizer gives enlightening insights about the different regularization properties. |
| Tasks | Deblurring, Denoising, Image Denoising, Image Restoration |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08488v1 |
| https://arxiv.org/pdf/1907.08488v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimal-control-approach-to-early-stopping |
| Repo | |
| Framework | |
Edge Heuristic GAN for Non-uniform Blind Deblurring
| Title | Edge Heuristic GAN for Non-uniform Blind Deblurring |
| Authors | Shuai Zheng, Zhenfeng Zhu, Jian Cheng, Yandong Guo, Yao Zhao |
| Abstract | Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation. However, the traditional blind deblurring methods based on blur kernel estimation do not perform well on complicated non-uniform motion blurs. Recent studies show that GAN-based approaches achieve impressive performance on deblurring tasks. In this letter, to further improve the performance of GAN-based methods on deblurring tasks, we propose an edge heuristic multi-scale generative adversarial network(GAN), which uses the “coarse-to-fine” scheme to restore clear images in an end-to-end manner. In particular, an edge-enhanced network is designed to generate sharp edges as auxiliary information to guide the deblurring process. Furthermore, We propose a hierarchical content loss function for deblurring tasks. Extensive experiments on different datasets show that our method achieves state-of-the-art performance in dynamic scene deblurring. |
| Tasks | Deblurring |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05185v1 |
| https://arxiv.org/pdf/1907.05185v1.pdf | |
| PWC | https://paperswithcode.com/paper/edge-heuristic-gan-for-non-uniform-blind |
| Repo | |
| Framework | |
OGNet: Salient Object Detection with Output-guided Attention Module
| Title | OGNet: Salient Object Detection with Output-guided Attention Module |
| Authors | Shiping Zhu, Lanyun Zhu |
| Abstract | Attention mechanisms are widely used in salient object detection models based on deep learning, which can effectively promote the extraction and utilization of useful information by neural networks. However, most of the existing attention modules used in salient object detection are input with the processed feature map itself, which easily leads to the problem of blind overconfidence'. In this paper, instead of applying the widely used self-attention module, we present an output-guided attention module built with multi-scale outputs to overcome the problem of blind overconfidence’. We also construct a new loss function, the intractable area F-measure loss function, which is based on the F-measure of the hard-to-handle area to improve the detection effect of the model in the edge areas and confusing areas of an image. Extensive experiments and abundant ablation studies are conducted to evaluate the effect of our methods and to explore the most suitable structure for the model. Tests on several data sets show that our model performs very well, even though it is very lightweight. |
| Tasks | Object Detection, Salient Object Detection |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07449v1 |
| https://arxiv.org/pdf/1907.07449v1.pdf | |
| PWC | https://paperswithcode.com/paper/ognet-salient-object-detection-with-output |
| Repo | |
| Framework | |
Improving the dynamics of quantum sensors with reinforcement learning
| Title | Improving the dynamics of quantum sensors with reinforcement learning |
| Authors | Jonas Schuff, Lukas J. Fiderer, Daniel Braun |
| Abstract | Recently proposed quantum-chaotic sensors achieve quantum enhancements in measurement precision by applying nonlinear control pulses to the dynamics of the quantum sensor while using classical initial states that are easy to prepare. Here, we use the cross-entropy method of reinforcement learning to optimize the strength and position of control pulses. Compared to the quantum-chaotic sensors with periodic control pulses in the presence of superradiant damping, we find that decoherence can be fought even better and measurement precision can be enhanced further by optimizing the control. In some examples, we find enhancements in sensitivity by more than an order of magnitude. By visualizing the evolution of the quantum state, the mechanism exploited by the reinforcement learning method is identified as a kind of spin-squeezing strategy that is adapted to the superradiant damping. |
| Tasks | |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08416v2 |
| https://arxiv.org/pdf/1908.08416v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-the-dynamics-of-quantum-sensors |
| Repo | |
| Framework | |
Interleaved Multitask Learning for Audio Source Separation with Independent Databases
| Title | Interleaved Multitask Learning for Audio Source Separation with Independent Databases |
| Authors | Clement S. J. Doire, Olumide Okubadejo |
| Abstract | Deep Neural Network-based source separation methods usually train independent models to optimize for the separation of individual sources. Although this can lead to good performance for well-defined targets, it can also be computationally expensive. The multitask alternative of a single network jointly optimizing for all targets simultaneously usually requires the availability of all target sources for each input. This requirement hampers the ability to create large training databases. In this paper, we present a model that decomposes the learnable parameters into a shared parametric model (encoder) and independent components (decoders) specific to each source. We propose an interleaved training procedure that optimizes the sub-task decoders independently and thus does not require each sample to possess a ground truth for all of its composing sources. Experimental results on MUSDB18 with the proposed method show comparable performance to independently trained models, with less trainable parameters, more efficient inference, and an encoder transferable to future target objectives. The results also show that using the proposed interleaved training procedure leads to better Source-to-Interference energy ratios when compared to the simultaneous optimization of all training objectives, even when all composing sources are available. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05182v1 |
| https://arxiv.org/pdf/1908.05182v1.pdf | |
| PWC | https://paperswithcode.com/paper/interleaved-multitask-learning-for-audio |
| Repo | |
| Framework | |
Practical Bayesian Optimization over Sets
| Title | Practical Bayesian Optimization over Sets |
| Authors | Jungtaek Kim, Michael McCourt, Tackgeun You, Saehoon Kim, Seungjin Choi |
| Abstract | We propose a practical Bayesian optimization method over sets, to minimize a black-box function that can take a set as a single input. Because set inputs are permutation-invariant and variable-length, traditional Gaussian process-based Bayesian optimization strategies which assume vector inputs can fall short. To address this, we develop a Bayesian optimization method with \emph{set kernel} that is used to build surrogate functions. This kernel accumulates similarity over set elements to enforce permutation-invariance and permit sets of variable size, but this comes at a greater computational cost. To reduce this burden, we propose two key components: (i) a more efficient probabilistic approximation which is still positive-definite and is an unbiased estimator of the true set kernel with upper-bounded variance in terms of the number of subsamples, (ii) a constrained acquisition function optimization over sets, which uses symmetry of the feasible region that defines a set input. Finally, we present several numerical experiments which demonstrate that our method outperforms other methods in various applications. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09780v2 |
| https://arxiv.org/pdf/1905.09780v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimization-over-sets |
| Repo | |
| Framework | |
Deep RAN: A Scalable Data-driven platform to Detect Anomalies in Live Cellular Network Using Recurrent Convolutional Neural Network
| Title | Deep RAN: A Scalable Data-driven platform to Detect Anomalies in Live Cellular Network Using Recurrent Convolutional Neural Network |
| Authors | Mohammad Rasoul Tanhatalab, Hossein Yousefi, Hesam Mohammad Hosseini, Mostafa Mofarah Bonab, Vahid Fakharian, Hadis Abarghouei |
| Abstract | In this paper, we propose a novel algorithm to detect anomaly in terms of Key Parameter Indicators (KPI)s over live cellular networks based on the combination of Recurrent Neural Networks (RNN), and Convolutional Neural Networks (CNN), as Recurrent Convolutional Neural Networks (R-CNN). CNN models the spatial correlations and information, whereas, RNN models the temporal correlations and information. In this paper, the studied cellular network consists of 2G, 3G, 4G, and 4.5G technologies, and the KPIs include Voice and data traffic of the cells. The data and voice traffic are extremely important for the owner of wireless networks because it is directly related to the revenue and quality of service that users experience. These traffic changes happen due to a couple of reasons: the subscriber behavior changes due to special events, making neighbor sites on-air or down, or by shifting the traffic to the other technologies, e.g. shifting the traffic from 3G to 4G. Traditionally, in order to keep the network stable, the traffic should be observed layer by layer during each interval to detect major changes in KPIs, in large scale telecommunication networks it will be too time-consuming with the low accuracy of anomaly detection. However, the proposed algorithm is capable of detecting the abnormal KPIs for each element of the network in a time-efficient and accurate manner. It observes the traffic layer trends and classifies them into 8 traffic categories: Normal, Suddenly Increasing, Gradually Increasing, Suddenly Decreasing, Gradually Decreasing, Faulty Site, New Site, and Down Site. This classification task enables the vendors and operators to detect anomalies in their live networks in order to keep the KPIs in a normal trend. The algorithm is trained and tested on the real dataset over a cellular network with more than 25000 cells. |
| Tasks | Anomaly Detection |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.04472v1 |
| https://arxiv.org/pdf/1911.04472v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-ran-a-scalable-data-driven-platform-to |
| Repo | |
| Framework | |
3D tissue reconstruction with Kinect to evaluate neck lymphedema
| Title | 3D tissue reconstruction with Kinect to evaluate neck lymphedema |
| Authors | Gerrit Brugman, Beril Sirmacek |
| Abstract | Lymphedema is a condition of localized tissue swelling caused by a damaged lymphatic system. Therapy to these tissues is applied manually. Some of the methods are lymph drainage, compression therapy or bandaging. However, the therapy methods are still insufficiently evaluated. Especially, because of not having a reliable method to measure the change of such a soft and flexible tissue. In this research, our goal has been providing a 3d computer vision based method to measure the changes of the neck tissues. To do so, we used Kinect as a depth sensor and built our algorithms for the point cloud data acquired from this sensor. The resulting 3D models of the patient necks are used for comparing the models in time and measuring the volumetric changes accurately. Our discussions with the medical doctors validate that, when used in practice this approach would be able to give better indication on which therapy method is helping and how the tissue is changing in time. |
| Tasks | |
| Published | 2019-11-02 |
| URL | https://arxiv.org/abs/1911.00678v1 |
| https://arxiv.org/pdf/1911.00678v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-tissue-reconstruction-with-kinect-to |
| Repo | |
| Framework | |
A Road-map Towards Explainable Question Answering A Solution for Information Pollution
| Title | A Road-map Towards Explainable Question Answering A Solution for Information Pollution |
| Authors | Saeedeh Shekarpour, Faisal Alshargi |
| Abstract | The increasing rate of information pollution on the Web requires novel solutions to tackle that. Question Answering (QA) interfaces are simplified and user-friendly interfaces to access information on the Web. However, similar to other AI applications, they are black boxes which do not manifest the details of the learning or reasoning steps for augmenting an answer. The Explainable Question Answering (XQA) system can alleviate the pain of information pollution where it provides transparency to the underlying computational model and exposes an interface enabling the end-user to access and validate provenance, validity, context, circulation, interpretation, and feedbacks of information. This position paper sheds light on the core concepts, expectations, and challenges in favor of the following questions (i) What is an XQA system?, (ii) Why do we need XQA?, (iii) When do we need XQA? (iv) How to represent the explanations? (iv) How to evaluate XQA systems? |
| Tasks | Question Answering |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02606v1 |
| https://arxiv.org/pdf/1907.02606v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-road-map-towards-explainable-question |
| Repo | |
| Framework | |
Segment Relevance Estimation for Audio Analysis and Weakly-Labelled Classification
| Title | Segment Relevance Estimation for Audio Analysis and Weakly-Labelled Classification |
| Authors | Juliano Henrique Foleiss, Tiago Fernandes Tavares |
| Abstract | We propose a method that quantifies the importance, namely relevance, of audio segments for classification in weakly-labelled problems. It works by drawing information from a set of class-wise one-vs-all classifiers. By selecting the classifiers used in each specific classification problem, the relevance measure adapts to different user-defined viewpoints without requiring additional neural network training. This characteristic allows the relevance measure to highlight audio segments that quickly adapt to user-defined criteria. Such functionality can be used for computer-assisted audio analysis. Also, we propose a neural network architecture, namely RELNET, that leverages the relevance measure for weakly-labelled audio classification problems. RELNET was evaluated in the DCASE2018 dataset and achieved competitive classification results when compared to previous attention-based proposals. |
| Tasks | Audio Classification |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04666v1 |
| https://arxiv.org/pdf/1911.04666v1.pdf | |
| PWC | https://paperswithcode.com/paper/segment-relevance-estimation-for-audio |
| Repo | |
| Framework | |
GRASPEL: Graph Spectral Learning at Scale
| Title | GRASPEL: Graph Spectral Learning at Scale |
| Authors | Yongyu Wang, Zhiqiang Zhao, Zhuo Feng |
| Abstract | Learning meaningful graphs from data plays important roles in many data mining and machine learning tasks, such as data representation and analysis, dimension reduction, data clustering, and visualization, etc. In this work, for the first time, we present a highly-scalable spectral approach (GRASPEL) for learning large graphs from data. By limiting the precision matrix to be a graph Laplacian, our approach aims to estimate ultra-sparse (tree-like) weighted undirected graphs and shows a clear connection with the prior graphical Lasso method. By interleaving the latest high-performance nearly-linear time spectral methods for graph sparsification, coarsening and embedding, ultra-sparse yet spectrally-robust graphs can be learned by identifying and including the most spectrally-critical edges into the graph. Compared with prior state-of-the-art graph learning approaches, GRASPEL is more scalable and allows substantially improving computing efficiency and solution quality of a variety of data mining and machine learning applications, such as spectral clustering (SC), and t-Distributed Stochastic Neighbor Embedding (t-SNE). {For example, when comparing with graphs constructed using existing methods, GRASPEL achieved the best spectral clustering efficiency and accuracy. |
| Tasks | Dimensionality Reduction |
| Published | 2019-11-23 |
| URL | https://arxiv.org/abs/1911.10373v1 |
| https://arxiv.org/pdf/1911.10373v1.pdf | |
| PWC | https://paperswithcode.com/paper/graspel-graph-spectral-learning-at-scale-1 |
| Repo | |
| Framework | |
Applications of Social Media in Hydroinformatics: A Survey
| Title | Applications of Social Media in Hydroinformatics: A Survey |
| Authors | Yufeng Yu, Yuelong Zhu, Dingsheng Wan, Qun Zhao, Kai Shu, Huan Liu |
| Abstract | Floods of research and practical applications employ social media data for a wide range of public applications, including environmental monitoring, water resource managing, disaster and emergency response.Hydroinformatics can benefit from the social media technologies with newly emerged data, techniques and analytical tools to handle large datasets, from which creative ideas and new values could be mined.This paper first proposes a 4W (What, Why, When, hoW) model and a methodological structure to better understand and represent the application of social media to hydroinformatics, then provides an overview of academic research of applying social media to hydroinformatics such as water environment, water resources, flood, drought and water Scarcity management. At last,some advanced topics and suggestions of water related social media applications from data collection, data quality management, fake news detection, privacy issues, algorithms and platforms was present to hydroinformatics managers and researchers based on previous discussion. |
| Tasks | Fake News Detection |
| Published | 2019-05-01 |
| URL | http://arxiv.org/abs/1905.03035v1 |
| http://arxiv.org/pdf/1905.03035v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503035 |
| Repo | |
| Framework | |
