January 27, 2020

2837 words 14 mins read

Paper Group ANR 1332

On the Minimax Optimality of Estimating the Wasserstein Metric. Soft-ranking Label Encoding for Robust Facial Age Estimation. Customizing Pareto Simulated Annealing for Multi-objective Optimization of Control Cabinet Layout. Truck Traffic Monitoring with Satellite Images. ViewSynth: Learning Local Features from Depth using View Synthesis. Fast Mult …

On the Minimax Optimality of Estimating the Wasserstein Metric


Title	On the Minimax Optimality of Estimating the Wasserstein Metric
Authors	Tengyuan Liang
Abstract	We study the minimax optimal rate for estimating the Wasserstein-$1$ metric between two unknown probability measures based on $n$ i.i.d. empirical samples from them. We show that estimating the Wasserstein metric itself between probability measures, is not significantly easier than estimating the probability measures under the Wasserstein metric. We prove that the minimax optimal rates for these two problems are multiplicatively equivalent, up to a $\log \log (n)/\log (n)$ factor.
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10324v1
PDF	https://arxiv.org/pdf/1908.10324v1.pdf
PWC	https://paperswithcode.com/paper/on-the-minimax-optimality-of-estimating-the
Repo
Framework

Soft-ranking Label Encoding for Robust Facial Age Estimation


Title	Soft-ranking Label Encoding for Robust Facial Age Estimation
Authors	Xusheng Zeng, Changxing Ding, Yonggang Wen, Dacheng Tao
Abstract	Automatic facial age estimation can be used in a wide range of real-world applications. However, this process is challenging due to the randomness and slowness of the aging process. Accordingly, in this paper, we propose a comprehensive framework aimed at overcoming the challenges associated with facial age estimation. First, we propose a novel age encoding method, referred to as ‘Soft-ranking’, which encodes two important properties of facial age, i.e., the ordinal property and the correlation between adjacent ages. Therefore, Soft-ranking provides a richer supervision signal for training deep models. Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods. Finally, since existing face databases for age estimation are generally small, deep models tend to suffer from an overfitting problem. To address this issue, we propose a novel regularization strategy to encourage deep models to learn more robust features from facial parts for age estimation purposes. Extensive experiments indicate that the proposed techniques improve the age estimation performance; moreover, we achieve state-of-the-art performance on the three most popular age databases, $i.e.$, Morph II, CLAP2015, and CLAP2016.
Tasks	Age Estimation
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03625v1
PDF	https://arxiv.org/pdf/1906.03625v1.pdf
PWC	https://paperswithcode.com/paper/soft-ranking-label-encoding-for-robust-facial
Repo
Framework

Customizing Pareto Simulated Annealing for Multi-objective Optimization of Control Cabinet Layout


Title	Customizing Pareto Simulated Annealing for Multi-objective Optimization of Control Cabinet Layout
Authors	Sabri Pllana, Suejb Memeti, Joanna Kolodziej
Abstract	Determining the optimal location of control cabinet components requires the exploration of a large configuration space. For real-world control cabinets it is impractical to evaluate all possible cabinet configurations. Therefore, we need to apply methods for intelligent exploration of cabinet configuration space that enable to find a near-optimal configuration without evaluation of all possible configurations. In this paper, we describe an approach for multi-objective optimization of control cabinet layout that is based on Pareto Simulated Annealing. Optimization aims at minimizing the total wire length used for interconnection of components and the heat convection within the cabinet. We simulate heat convection to study the warm air flow within the control cabinet and determine the optimal position of components that generate heat during the operation. We evaluate and demonstrate the effectiveness of our approach empirically for various control cabinet sizes and usage scenarios.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.04825v1
PDF	https://arxiv.org/pdf/1906.04825v1.pdf
PWC	https://paperswithcode.com/paper/customizing-pareto-simulated-annealing-for
Repo
Framework

Truck Traffic Monitoring with Satellite Images


Title	Truck Traffic Monitoring with Satellite Images
Authors	Lynn H. Kaack, George H. Chen, M. Granger Morgan
Abstract	The road freight sector is responsible for a large and growing share of greenhouse gas emissions, but reliable data on the amount of freight that is moved on roads in many parts of the world are scarce. Many low- and middle-income countries have limited ground-based traffic monitoring and freight surveying activities. In this proof of concept, we show that we can use an object detection network to count trucks in satellite images and predict average annual daily truck traffic from those counts. We describe a complete model, test the uncertainty of the estimation, and discuss the transfer to developing countries.
Tasks	Object Detection
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07660v1
PDF	https://arxiv.org/pdf/1907.07660v1.pdf
PWC	https://paperswithcode.com/paper/truck-traffic-monitoring-with-satellite
Repo
Framework

ViewSynth: Learning Local Features from Depth using View Synthesis


Title	ViewSynth: Learning Local Features from Depth using View Synthesis
Authors	Jisan Mahmud, Peri Akiva, Rajat Vikram Singh, Spondon Kundu, Kuan-Chuan Peng, Jan-Michael Frahm
Abstract	We address the problem of jointly detecting keypoints and learning descriptors in depth data with challenging viewpoint changes. Despite great improvements in recent RGB based local feature learning methods, we show that these methods cannot be directly transferred to the depth image modality. These methods also do not utilize the 2.5D information present in depth images. We propose a framework ViewSynth, designed to jointly learn 3D structure aware depth image representation, and local features from that representation. ViewSynth consists of `View Synthesis Network’ (VSN), trained to synthesize depth image views given a depth image representation and query viewpoints. ViewSynth framework includes joint learning of keypoints and feature descriptor, paired with our view synthesis loss, which guides the model to propose keypoints robust to viewpoint changes. We demonstrate the effectiveness of our formulation on several depth image datasets, where learned local features using our proposed ViewSynth framework outperforms the state-of-the-art methods in keypoint matching and camera localization tasks. \|
Tasks	Camera Localization
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10248v1
PDF	https://arxiv.org/pdf/1911.10248v1.pdf
PWC	https://paperswithcode.com/paper/viewsynth-learning-local-features-from-depth
Repo
Framework

Fast Multi-language LSTM-based Online Handwriting Recognition


Title	Fast Multi-language LSTM-based Online Handwriting Recognition
Authors	Victor Carbune, Pedro Gonnet, Thomas Deselaers, Henry A. Rowley, Alexander Daryin, Marcos Calvo, Li-Lun Wang, Daniel Keysers, Sandro Feuz, Philippe Gervais
Abstract	We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture. This new system has completely replaced our previous Segment-and-Decode-based system and reduced the error rate by 20%-40% relative for most languages. Further, we report new state-of-the-art results on IAM-OnDB for both the open and closed dataset setting. The system combines methods from sequence recognition with a new input encoding using B'ezier curves. This leads to up to 10x faster recognition times compared to our previous system. Through a series of experiments we determine the optimal configuration of our models and report the results of our setup on a number of additional public datasets.
Tasks
Published	2019-02-22
URL	https://arxiv.org/abs/1902.10525v2
PDF	https://arxiv.org/pdf/1902.10525v2.pdf
PWC	https://paperswithcode.com/paper/fast-multi-language-lstm-based-online
Repo
Framework

SAR Image Change Detection via Spatial Metric Learning with an Improved Mahalanobis Distance


Title	SAR Image Change Detection via Spatial Metric Learning with an Improved Mahalanobis Distance
Authors	Rongfang Wang, Jia-Wei Chen, Yule Wang, Licheng Jiao, Mi Wang
Abstract	The log-ratio (LR) operator has been widely employed to generate the difference image for synthetic aperture radar (SAR) image change detection. However, the difference image generated by this pixel-wise operator can be subject to SAR images speckle and unavoidable registration errors between bitemporal SAR images. In this letter, we proposed a spatial metric learning method to obtain a difference image more robust to the speckle by learning a metric from a set of constraint pairs. In the proposed method, spatial context is considered in constructing constraint pairs, each of which consists of patches in the same location of bitemporal SAR images. Then, a semi-definite positive metric matrix $\bf M$ can be obtained by the optimization with the max-margin criterion. Finally, we verify our proposed method on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that the difference map obtained by our proposed method outperforms than other state-of-art methods.
Tasks	Metric Learning
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07930v1
PDF	https://arxiv.org/pdf/1906.07930v1.pdf
PWC	https://paperswithcode.com/paper/sar-image-change-detection-via-spatial-metric
Repo
Framework

Devil in the Detail: Attack Scenarios in Industrial Applications


Title	Devil in the Detail: Attack Scenarios in Industrial Applications
Authors	Simon D. Duque Anton, Alexander Hafner, Hans Dieter Schotten
Abstract	In the past years, industrial networks have become increasingly interconnected and opened to private or public networks. This leads to an increase in efficiency and manageability, but also increases the attack surface. Industrial networks often consist of legacy systems that have not been designed with security in mind. In the last decade, an increase in attacks on cyber-physical systems was observed, with drastic consequences on the physical work. In this work, attack vectors on industrial networks are categorised. A real-world process is simulated, attacks are then introduced. Finally, two machine learning-based methods for time series anomaly detection are employed to detect the attacks. Matrix Profiles are employed more successfully than a predictor Long Short-Term Memory network, a class of neural networks.
Tasks	Anomaly Detection, Time Series
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10292v1
PDF	https://arxiv.org/pdf/1905.10292v1.pdf
PWC	https://paperswithcode.com/paper/devil-in-the-detail-attack-scenarios-in
Repo
Framework

DiPCo – Dinner Party Corpus


Title	DiPCo – Dinner Party Corpus
Authors	Maarten Van Segbroeck, Ahmed Zaid, Ksenia Kutsenko, Cirenia Huerta, Tinh Nguyen, Xuewen Luo, Björn Hoffmeister, Jan Trmal, Maurizio Omologo, Roland Maas
Abstract	We present a speech data corpus that simulates a “dinner party” scenario taking place in an everyday home environment. The corpus was created by recording multiple groups of four Amazon employee volunteers having a natural conversation in English around a dining table. The participants were recorded by a single-channel close-talk microphone and by five far-field 7-microphone array devices positioned at different locations in the recording room. The dataset contains the audio recordings and human labeled transcripts of a total of 10 sessions with a duration between 15 and 45 minutes. The corpus was created to advance in the field of noise robust and distant speech processing and is intended to serve as a public research and benchmarking data set.
Tasks
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13447v1
PDF	https://arxiv.org/pdf/1909.13447v1.pdf
PWC	https://paperswithcode.com/paper/dipco-dinner-party-corpus
Repo
Framework

Detecting Vietnamese Opinion Spam


Title	Detecting Vietnamese Opinion Spam
Authors	T. H. H Duong, T. D. Vu, V. M. Ngo
Abstract	Recently, Vietnamese Natural Language Processing has been researched by experts in academic and business. However, the existing papers have been focused only on information classification or extraction from documents. Nowadays, with quickly development of the e-commerce websites, forums and social networks, the products, people, organizations or wonders are targeted of comments or reviews of the network communities. Many people often use that reviews to make their decision on something. Whereas, there are many people or organizations use the reviews to mislead readers. Therefore, it is so necessary to detect those bad behaviors in reviews. In this paper, we research this problem and propose an appropriate method for detecting Vietnamese reviews being spam or non-spam. The accuracy of our method is up to 90%.
Tasks
Published	2019-05-09
URL	https://arxiv.org/abs/1905.06112v1
PDF	https://arxiv.org/pdf/1905.06112v1.pdf
PWC	https://paperswithcode.com/paper/190506112
Repo
Framework

SACOBRA with Online Whitening for Solving Optimization Problems with High Conditioning


Title	SACOBRA with Online Whitening for Solving Optimization Problems with High Conditioning
Authors	Samineh Bagheri, Wolfgang Konen, Thomas Bäck
Abstract	Real-world optimization problems often have expensive objective functions in terms of cost and time. It is desirable to find near-optimal solutions with very few function evaluations. Surrogate-assisted optimizers tend to reduce the required number of function evaluations by replacing the real function with an efficient mathematical model built on few evaluated points. Problems with a high condition number are a challenge for many surrogate-assisted optimizers including SACOBRA. To address such problems we propose a new online whitening operating in the black-box optimization paradigm. We show on a set of high-conditioning functions that online whitening tackles SACOBRA’s early stagnation issue and reduces the optimization error by a factor between 10 to 1e12 as compared to the plain SACOBRA, though it imposes many extra function evaluations. Covariance matrix adaptation evolution strategy (CMA-ES) has for very high numbers of function evaluations even lower errors, whereas SACOBRA performs better in the expensive setting (less than 1e03 function evaluations). If we count all parallelizable function evaluations (population evaluation in CMA-ES, online whitening in our approach) as one iteration, then both algorithms have comparable strength even on the long run. This holds for problems with dimension D <= 20.
Tasks
Published	2019-04-17
URL	http://arxiv.org/abs/1904.08397v1
PDF	http://arxiv.org/pdf/1904.08397v1.pdf
PWC	https://paperswithcode.com/paper/sacobra-with-online-whitening-for-solving
Repo
Framework

Estimating Real Log Canonical Thresholds


Title	Estimating Real Log Canonical Thresholds
Authors	Toru Imai
Abstract	Evaluation of the marginal likelihood plays an important role in model selection problems. The widely applicable Bayesian information criterion (WBIC) and singular Bayesian information criterion (sBIC) give approximations to the log marginal likelihood, which can be applied to both regular and singular models. When the real log canonical thresholds are known, the performance of sBIC is considered to be better than that of WBIC, but only few real log canonical thresholds are known. In this paper, we propose a new estimator of the real log canonical thresholds based on the variance of thermodynamic integration with an inverse temperature. In addition, we propose an application to make sBIC widely applicable. Finally, we investigate the performance of the estimator and model selection by simulation studies and application to real data.
Tasks	Model Selection
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01341v2
PDF	https://arxiv.org/pdf/1906.01341v2.pdf
PWC	https://paperswithcode.com/paper/estimating-real-log-canonical-thresholds
Repo
Framework

A customisable pipeline for continuously harvesting socially-minded Twitter users


Title	A customisable pipeline for continuously harvesting socially-minded Twitter users
Authors	Flavio Primo, Paolo Missier, Alexander Romanovsky, Mickael Figueredo, Nelio Cacho
Abstract	On social media platforms and Twitter in particular, specific classes of users such as influencers have been given satisfactory operational definitions in terms of network and content metrics. Others, for instance online activists, are not less important but their characterisation still requires experimenting. We make the hypothesis that such interesting users can be found within temporally and spatially localised contexts, i.e., small but topical fragments of the network containing interactions about social events or campaigns with a significant footprint on Twitter. To explore this hypothesis, we have designed a continuous user profile discovery pipeline that produces an ever-growing dataset of user profiles by harvesting and analysing contexts from the Twitter stream. The profiles dataset includes key network and content-based users metrics, enabling experimentation with user-defined score functions that characterise specific classes of online users. The paper describes the design and implementation of the pipeline and its empirical evaluation on a case study consisting of healthcare-related campaigns in the UK, showing how it supports the operational definitions of online activism, by comparing three experimental ranking functions. The code is publicly available.
Tasks
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07061v1
PDF	http://arxiv.org/pdf/1903.07061v1.pdf
PWC	https://paperswithcode.com/paper/a-customisable-pipeline-for-continuously
Repo
Framework

Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory


Title	Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory
Authors	Minju Jung, Takazumi Matsumoto, Jun Tani
Abstract	Mental simulation is a critical cognitive function for goal-directed behavior because it is essential for assessing actions and their consequences. When a self-generated or externally specified goal is given, a sequence of actions that is most likely to attain that goal is selected among other candidates via mental simulation. Therefore, better mental simulation leads to better goal-directed action planning. However, developing a mental simulation model is challenging because it requires knowledge of self and the environment. The current paper studies how adequate goal-directed action plans of robots can be mentally generated by dynamically organizing top-down visual attention and visual working memory. For this purpose, we propose a neural network model based on variational Bayes predictive coding, where goal-directed action planning is formulated by Bayesian inference of latent intentional space. Our experimental results showed that cognitively meaningful competencies, such as autonomous top-down attention to the robot end effector (its hand) as well as dynamic organization of occlusion-free visual working memory, emerged. Furthermore, our analysis of comparative experiments indicated that introduction of visual working memory and the inference mechanism using variational Bayes predictive coding significantly improve the performance in planning adequate goal-directed actions.
Tasks	Bayesian Inference
Published	2019-03-12
URL	http://arxiv.org/abs/1903.04932v1
PDF	http://arxiv.org/pdf/1903.04932v1.pdf
PWC	https://paperswithcode.com/paper/goal-directed-behavior-under-variational
Repo
Framework

Adaptive Image-Feature Learning for Disease Classification Using Inductive Graph Networks


Title	Adaptive Image-Feature Learning for Disease Classification Using Inductive Graph Networks
Authors	Hendrik Burwinkel, Anees Kazi, Gerome Vivar, Shadi Albarqouni, Guillaume Zahnd, Nassir Navab, Seyed-Ahmad Ahmadi
Abstract	Recently, Geometric Deep Learning (GDL) has been introduced as a novel and versatile framework for computer-aided disease classification. GDL uses patient meta-information such as age and gender to model patient cohort relations in a graph structure. Concepts from graph signal processing are leveraged to learn the optimal mapping of multi-modal features, e.g. from images to disease classes. Related studies so far have considered image features that are extracted in a pre-processing step. We hypothesize that such an approach prevents the network from optimizing feature representations towards achieving the best performance in the graph network. We propose a new network architecture that exploits an inductive end-to-end learning approach for disease classification, where filters from both the CNN and the graph are trained jointly. We validate this architecture against state-of-the-art inductive graph networks and demonstrate significantly improved classification scores on a modified MNIST toy dataset, as well as comparable classification results with higher stability on a chest X-ray image dataset. Additionally, we explain how the structural information of the graph affects both the image filters and the feature learning.
Tasks
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03036v2
PDF	https://arxiv.org/pdf/1905.03036v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-image-feature-learning-for-disease
Repo
Framework