July 28, 2019

3296 words 16 mins read

Paper Group ANR 192

Optimal Detection of Faulty Traffic Sensors Used in Route Planning. Cystoid macular edema segmentation of Optical Coherence Tomography images using fully convolutional neural networks and fully connected CRFs. Elliptical modeling and pattern analysis for perturbation models and classfication. Scene-adapted plug-and-play algorithm with convergence g …

Optimal Detection of Faulty Traffic Sensors Used in Route Planning


Title	Optimal Detection of Faulty Traffic Sensors Used in Route Planning
Authors	Amin Ghafouri, Aron Laszka, Abhishek Dubey, Xenofon Koutsoukos
Abstract	In a smart city, real-time traffic sensors may be deployed for various applications, such as route planning. Unfortunately, sensors are prone to failures, which result in erroneous traffic data. Erroneous data can adversely affect applications such as route planning, and can cause increased travel time. To minimize the impact of sensor failures, we must detect them promptly and accurately. However, typical detection algorithms may lead to a large number of false positives (i.e., false alarms) and false negatives (i.e., missed detections), which can result in suboptimal route planning. In this paper, we devise an effective detector for identifying faulty traffic sensors using a prediction model based on Gaussian Processes. Further, we present an approach for computing the optimal parameters of the detector which minimize losses due to false-positive and false-negative errors. We also characterize critical sensors, whose failure can have high impact on the route planning application. Finally, we implement our method and evaluate it numerically using a real-world dataset and the route planning platform OpenTripPlanner.
Tasks	Gaussian Processes
Published	2017-02-08
URL	http://arxiv.org/abs/1702.02628v2
PDF	http://arxiv.org/pdf/1702.02628v2.pdf
PWC	https://paperswithcode.com/paper/optimal-detection-of-faulty-traffic-sensors
Repo
Framework

Cystoid macular edema segmentation of Optical Coherence Tomography images using fully convolutional neural networks and fully connected CRFs


Title	Cystoid macular edema segmentation of Optical Coherence Tomography images using fully convolutional neural networks and fully connected CRFs
Authors	Fangliang Bai, Manuel J. Marques, Stuart J. Gibson
Abstract	In this paper we present a new method for cystoid macular edema (CME) segmentation in retinal Optical Coherence Tomography (OCT) images, using a fully convolutional neural network (FCN) and a fully connected conditional random fields (dense CRFs). As a first step, the framework trains the FCN model to extract features from retinal layers in OCT images, which exhibit CME, and then segments CME regions using the trained model. Thereafter, dense CRFs are used to refine the segmentation according to the edema appearance. We have trained and tested the framework with OCT images from 10 patients with diabetic macular edema (DME). Our experimental results show that fluid and concrete macular edema areas were segmented with good adherence to boundaries. A segmentation accuracy of $0.61\pm 0.21$ (Dice coefficient) was achieved, with respect to the ground truth, which compares favourably with the previous state-of-the-art that used a kernel regression based method ($0.51\pm 0.34$). Our approach is versatile and we believe it can be easily adapted to detect other macular defects.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05324v1
PDF	http://arxiv.org/pdf/1709.05324v1.pdf
PWC	https://paperswithcode.com/paper/cystoid-macular-edema-segmentation-of-optical
Repo
Framework

Elliptical modeling and pattern analysis for perturbation models and classfication


Title	Elliptical modeling and pattern analysis for perturbation models and classfication
Authors	Shan Suthaharan, Weining Shen
Abstract	The characteristics (or numerical patterns) of a feature vector in the transform domain of a perturbation model differ significantly from those of its corresponding feature vector in the input domain. These differences - caused by the perturbation techniques used for the transformation of feature patterns - degrade the performance of machine learning techniques in the transform domain. In this paper, we proposed a nonlinear parametric perturbation model that transforms the input feature patterns to a set of elliptical patterns, and studied the performance degradation issues associated with random forest classification technique using both the input and transform domain features. Compared with the linear transformation such as Principal Component Analysis (PCA), the proposed method requires less statistical assumptions and is highly suitable for the applications such as data privacy and security due to the difficulty of inverting the elliptical patterns from the transform domain to the input domain. In addition, we adopted a flexible block-wise dimensionality reduction step in the proposed method to accommodate the possible high-dimensional data in modern applications. We evaluated the empirical performance of the proposed method on a network intrusion data set and a biological data set, and compared the results with PCA in terms of classification performance and data privacy protection (measured by the blind source separation attack and signal interference ratio). Both results confirmed the superior performance of the proposed elliptical transformation.
Tasks	Dimensionality Reduction
Published	2017-10-22
URL	http://arxiv.org/abs/1710.07939v1
PDF	http://arxiv.org/pdf/1710.07939v1.pdf
PWC	https://paperswithcode.com/paper/elliptical-modeling-and-pattern-analysis-for
Repo
Framework

Scene-adapted plug-and-play algorithm with convergence guarantees


Title	Scene-adapted plug-and-play algorithm with convergence guarantees
Authors	Afonso M. Teodoro, José M. Bioucas-Dias, Mário A. T. Figueiredo
Abstract	Recent frameworks, such as the so-called plug-and-play, allow us to leverage the developments in image denoising to tackle other, and more involved, problems in image processing. As the name suggests, state-of-the-art denoisers are plugged into an iterative algorithm that alternates between a denoising step and the inversion of the observation operator. While these tools offer flexibility, the convergence of the resulting algorithm may be difficult to analyse. In this paper, we plug a state-of-the-art denoiser, based on a Gaussian mixture model, in the iterations of an alternating direction method of multipliers and prove the algorithm is guaranteed to converge. Moreover, we build upon the concept of scene-adapted priors where we learn a model targeted to a specific scene being imaged, and apply the proposed method to address the hyperspectral sharpening problem.
Tasks	Denoising, Image Denoising
Published	2017-02-08
URL	http://arxiv.org/abs/1702.02445v2
PDF	http://arxiv.org/pdf/1702.02445v2.pdf
PWC	https://paperswithcode.com/paper/scene-adapted-plug-and-play-algorithm-with-1
Repo
Framework

Dynamic Capacity Estimation in Hopfield Networks


Title	Dynamic Capacity Estimation in Hopfield Networks
Authors	Saarthak Sarup, Mingoo Seok
Abstract	Understanding the memory capacity of neural networks remains a challenging problem in implementing artificial intelligence systems. In this paper, we address the notion of capacity with respect to Hopfield networks and propose a dynamic approach to monitoring a network’s capacity. We define our understanding of capacity as the maximum number of stored patterns which can be retrieved when probed by the stored patterns. Prior work in this area has presented static expressions dependent on neuron count $N$, forcing network designers to assume worst-case input characteristics for bias and correlation when setting the capacity of the network. Instead, our model operates simultaneously with the learning Hopfield network and concludes on a capacity estimate based on the patterns which were stored. By continuously updating the crosstalk associated with the stored patterns, our model guards the network from overwriting its memory traces and exceeding its capacity. We simulate our model using artificially generated random patterns, which can be set to a desired bias and correlation, and observe capacity estimates between 93% and 97% accurate. As a result, our model doubles the memory efficiency of Hopfield networks in comparison to the static and worst-case capacity estimate while minimizing the risk of lost patterns.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05340v1
PDF	http://arxiv.org/pdf/1709.05340v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-capacity-estimation-in-hopfield
Repo
Framework

Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders


Title	Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders
Authors	Shan Luo, Leqi Zhu, Kaspar Althoefer, Hongbin Liu
Abstract	This paper presents a successful application of deep learning for object recognition based on acoustic data. The shortcomings of previously employed approaches where handcrafted features describing the acoustic data are being used, include limiting the capability of the found representation to be widely applicable and facing the risk of capturing only insignificant characteristics for a task. In contrast, there is no need to define the feature representation format when using multilayer/deep learning architecture methods: features can be learned from raw sensor data without defining discriminative characteristics a-priori. In this paper, stacked denoising autoencoders are applied to train a deep learning model. Knocking each object in our test set 120 times with a marker pen to obtain the auditory data, thirty different objects were successfully classified in our experiment and each object was knocked 120 times by a marker pen to obtain the auditory data. By employing the proposed deep learning framework, a high accuracy of 91.50% was achieved. A traditional method using handcrafted features with a shallow classifier was taken as a benchmark and the attained recognition rate was only 58.22%. Interestingly, a recognition rate of 82.00% was achieved when using a shallow classifier with raw acoustic data as input. In addition, we could show that the time taken to classify one object using deep learning was far less (by a factor of more than 6) than utilizing the traditional method. It was also explored how different model parameters in our deep architecture affect the recognition performance.
Tasks	Denoising, Object Recognition
Published	2017-08-15
URL	http://arxiv.org/abs/1708.04432v1
PDF	http://arxiv.org/pdf/1708.04432v1.pdf
PWC	https://paperswithcode.com/paper/knock-knock-acoustic-object-recognition-by
Repo
Framework

Probably approximate Bayesian computation: nonasymptotic convergence of ABC under misspecification


Title	Probably approximate Bayesian computation: nonasymptotic convergence of ABC under misspecification
Authors	James Ridgway
Abstract	Approximate Bayesian computation (ABC) is a widely used inference method in Bayesian statistics to bypass the point-wise computation of the likelihood. In this paper we develop theoretical bounds for the distance between the statistics used in ABC. We show that some versions of ABC are inherently robust to misspecification. The bounds are given in the form of oracle inequalities for a finite sample size. The dependence on the dimension of the parameter space and the number of statistics is made explicit. The results are shown to be amenable to oracle inequalities in parameter space. We apply our theoretical results to given prior distributions and data generating processes, including a non-parametric regression model. In a second part of the paper, we propose a sequential Monte Carlo (SMC) to sample from the pseudo-posterior, improving upon the state of the art samplers.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.05987v2
PDF	http://arxiv.org/pdf/1707.05987v2.pdf
PWC	https://paperswithcode.com/paper/probably-approximate-bayesian-computation
Repo
Framework

Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks


Title	Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
Authors	Hui Li, Peng Wang, Chunhua Shen
Abstract	In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks. We propose a unified network that simultaneously localizes and recognizes text with a single forward pass, avoiding intermediate processes like image cropping and feature re-calculation, word separation, or character grouping. In contrast to existing approaches that consider text detection and recognition as two distinct tasks and tackle them one by one, the proposed framework settles these two tasks concurrently. The whole framework can be trained end-to-end, requiring only images, the ground-truth bounding boxes and text labels. Through end-to-end training, the learned features can be more informative, which improves the overall performance. The convolutional features are calculated only once and shared by both detection and recognition, which saves processing time. Our proposed method has achieved competitive performance on several benchmark datasets.
Tasks	Image Cropping, Text Spotting
Published	2017-07-13
URL	http://arxiv.org/abs/1707.03985v1
PDF	http://arxiv.org/pdf/1707.03985v1.pdf
PWC	https://paperswithcode.com/paper/towards-end-to-end-text-spotting-with
Repo
Framework

Cascaded Segmentation-Detection Networks for Word-Level Text Spotting


Title	Cascaded Segmentation-Detection Networks for Word-Level Text Spotting
Authors	Siyang Qin, Roberto Manduchi
Abstract	We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text “in the wild”. Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000-by-560 image on a Titan X GPU, our system achieves the highest score to date among published algorithms on the ICDAR 2015 Incidental Scene Text dataset benchmark.
Tasks	Text Spotting
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00834v1
PDF	http://arxiv.org/pdf/1704.00834v1.pdf
PWC	https://paperswithcode.com/paper/cascaded-segmentation-detection-networks-for
Repo
Framework

Faster Coordinate Descent via Adaptive Importance Sampling


Title	Faster Coordinate Descent via Adaptive Importance Sampling
Authors	Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi
Abstract	Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive rules for the random selection of their updates. By adaptive, we mean that our selection rules are based on the dual residual or the primal-dual gap estimates and can change at each iteration. We theoretically characterize the performance of our selection rules and demonstrate improvements over the state-of-the-art, and extend our theory and algorithms to general convex objectives. Numerical evidence with hinge-loss support vector machines and Lasso confirm that the practice follows the theory.
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02518v1
PDF	http://arxiv.org/pdf/1703.02518v1.pdf
PWC	https://paperswithcode.com/paper/faster-coordinate-descent-via-adaptive
Repo
Framework

Truncation-free Hybrid Inference for DPMM


Title	Truncation-free Hybrid Inference for DPMM
Authors	Arnim Bleier
Abstract	Dirichlet process mixture models (DPMM) are a cornerstone of Bayesian non-parametrics. While these models free from choosing the number of components a-priori, computationally attractive variational inference often reintroduces the need to do so, via a truncation on the variational distribution. In this paper we present a truncation-free hybrid inference for DPMM, combining the advantages of sampling-based MCMC and variational methods. The proposed hybridization enables more efficient variational updates, while increasing model complexity only if needed. We evaluate the properties of the hybrid updates and their empirical performance in single- as well as mixed-membership models. Our method is easy to implement and performs favorably compared to existing schemas.
Tasks
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03743v1
PDF	http://arxiv.org/pdf/1701.03743v1.pdf
PWC	https://paperswithcode.com/paper/truncation-free-hybrid-inference-for-dpmm
Repo
Framework

Learning Spatio-temporal Features with Partial Expression Sequences for on-the-Fly Prediction


Title	Learning Spatio-temporal Features with Partial Expression Sequences for on-the-Fly Prediction
Authors	Wissam J. Baddar, Yong Man Ro
Abstract	Spatio-temporal feature encoding is essential for encoding facial expression dynamics in video sequences. At test time, most spatio-temporal encoding methods assume that a temporally segmented sequence is fed to a learned model, which could require the prediction to wait until the full sequence is available to an auxiliary task that performs the temporal segmentation. This causes a delay in predicting the expression. In an interactive setting, such as affective interactive agents, such delay in the prediction could not be tolerated. Therefore, training a model that can accurately predict the facial expression “on-the-fly” (as they are fed to the system) is essential. In this paper, we propose a new spatio-temporal feature learning method, which would allow prediction with partial sequences. As such, the prediction could be performed on-the-fly. The proposed method utilizes an estimated expression intensity to generate dense labels, which are used to regulate the prediction model training with a novel objective function. As results, the learned spatio-temporal features can robustly predict the expression with partial (incomplete) expression sequences, on-the-fly. Experimental results showed that the proposed method achieved higher recognition rates compared to the state-of-the-art methods on both datasets. More importantly, the results verified that the proposed method improved the prediction frames with partial expression sequence inputs.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10914v1
PDF	http://arxiv.org/pdf/1711.10914v1.pdf
PWC	https://paperswithcode.com/paper/learning-spatio-temporal-features-with
Repo
Framework

Person Re-Identification by Camera Correlation Aware Feature Augmentation


Title	Person Re-Identification by Camera Correlation Aware Feature Augmentation
Authors	Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, Jian-Huang Lai
Abstract	The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coRrelation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT.
Tasks	Person Re-Identification
Published	2017-03-26
URL	http://arxiv.org/abs/1703.08837v1
PDF	http://arxiv.org/pdf/1703.08837v1.pdf
PWC	https://paperswithcode.com/paper/person-re-identification-by-camera
Repo
Framework

Perturbative Black Box Variational Inference


Title	Perturbative Black Box Variational Inference
Authors	Robert Bamler, Cheng Zhang, Manfred Opper, Stephan Mandt
Abstract	Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as alpha divergences. In this paper, we view BBVI with generalized divergences as a form of estimating the marginal likelihood via biased importance sampling. The choice of divergence determines a bias-variance trade-off between the tightness of a bound on the marginal likelihood (low bias) and the variance of its gradient estimators. Drawing on variational perturbation theory of statistical physics, we use these insights to construct a family of new variational bounds. Enumerated by an odd integer order $K$, this family captures the standard KL bound for $K=1$, and converges to the exact marginal likelihood as $K\to\infty$. Compared to alpha-divergences, our reparameterization gradients have a lower variance. We show in experiments on Gaussian Processes and Variational Autoencoders that the new bounds are more mass covering, and that the resulting posterior covariances are closer to the true posterior and lead to higher likelihoods on held-out data.
Tasks	Gaussian Processes
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07433v2
PDF	http://arxiv.org/pdf/1709.07433v2.pdf
PWC	https://paperswithcode.com/paper/perturbative-black-box-variational-inference
Repo
Framework

Proceedings of the IJCAI 2017 Workshop on Learning in the Presence of Class Imbalance and Concept Drift (LPCICD’17)


Title	Proceedings of the IJCAI 2017 Workshop on Learning in the Presence of Class Imbalance and Concept Drift (LPCICD’17)
Authors	Shuo Wang, Leandro L. Minku, Nitesh Chawla, Xin Yao
Abstract	With the wide application of machine learning algorithms to the real world, class imbalance and concept drift have become crucial learning issues. Class imbalance happens when the data categories are not equally represented, i.e., at least one category is minority compared to other categories. It can cause learning bias towards the majority class and poor generalization. Concept drift is a change in the underlying distribution of the problem, and is a significant issue specially when learning from data streams. It requires learners to be adaptive to dynamic changes. Class imbalance and concept drift can significantly hinder predictive performance, and the problem becomes particularly challenging when they occur simultaneously. This challenge arises from the fact that one problem can affect the treatment of the other. For example, drift detection algorithms based on the traditional classification error may be sensitive to the imbalanced degree and become less effective; and class imbalance techniques need to be adaptive to changing imbalance rates, otherwise the class receiving the preferential treatment may not be the correct minority class at the current moment. Therefore, the mutual effect of class imbalance and concept drift should be considered during algorithm design. The aim of this workshop is to bring together researchers from the areas of class imbalance learning and concept drift in order to encourage discussions and new collaborations on solving the combined issue of class imbalance and concept drift. It provides a forum for international researchers and practitioners to share and discuss their original work on addressing new challenges and research issues in class imbalance learning, concept drift, and the combined issues of class imbalance and concept drift. The proceedings include 8 papers on these topics.
Tasks
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09425v1
PDF	http://arxiv.org/pdf/1707.09425v1.pdf
PWC	https://paperswithcode.com/paper/proceedings-of-the-ijcai-2017-workshop-on
Repo
Framework