July 28, 2019

3051 words 15 mins read

Paper Group ANR 316

Wasserstein Divergence for GANs. Preference Reasoning in Matching Procedures: Application to the Admission Post-Baccalaureat Platform. DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents. Recovering Homography from Camera Captured Documents using Convolutional Neural Networks. A Real- …

Wasserstein Divergence for GANs


Title	Wasserstein Divergence for GANs
Authors	Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc Van Gool
Abstract	In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and competitive qualitative performance. However, it is very challenging to approximate the $k$-Lipschitz constraint required by the Wasserstein-1 metric~(W-met). In this paper, we propose a novel Wasserstein divergence~(W-div), which is a relaxed version of W-met and does not require the $k$-Lipschitz constraint. As a concrete application, we introduce a Wasserstein divergence objective for GANs~(WGAN-div), which can faithfully approximate W-div through optimization. Under various settings, including progressive growing training, we demonstrate the stability of the proposed WGAN-div owing to its theoretical and practical advantages over WGANs. Also, we study the quantitative and visual performance of WGAN-div on standard image synthesis benchmarks of computer vision, showing the superior performance of WGAN-div compared to the state-of-the-art methods.
Tasks	Image Generation
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01026v4
PDF	http://arxiv.org/pdf/1712.01026v4.pdf
PWC	https://paperswithcode.com/paper/wasserstein-divergence-for-gans
Repo
Framework

Preference Reasoning in Matching Procedures: Application to the Admission Post-Baccalaureat Platform


Title	Preference Reasoning in Matching Procedures: Application to the Admission Post-Baccalaureat Platform
Authors	Youssef Hamadi, Souhila Kaci
Abstract	Because preferences naturally arise and play an important role in many real-life decisions, they are at the backbone of various fields. In particular preferences are increasingly used in almost all matching procedures-based applications. In this work we highlight the benefit of using AI insights on preferences in a large scale application, namely the French Admission Post-Baccalaureat Platform (APB). Each year APB allocates hundreds of thousands first year applicants to universities. This is done automatically by matching applicants preferences to university seats. In practice, APB can be unable to distinguish between applicants which leads to the introduction of random selection. This has created frustration in the French public since randomness, even used as a last mean does not fare well with the republican egalitarian principle. In this work, we provide a solution to this problem. We take advantage of recent AI Preferences Theory results to show how to enhance APB in order to improve expressiveness of applicants preferences and reduce their exposure to random decisions.
Tasks
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07298v3
PDF	http://arxiv.org/pdf/1707.07298v3.pdf
PWC	https://paperswithcode.com/paper/preference-reasoning-in-matching-procedures
Repo
Framework

DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents


Title	DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents
Authors	Gia-Hung Nguyen, Laure Soulier, Lynda Tamine, Nathalie Bricon-Souf
Abstract	The state-of-the-art solutions to the vocabulary mismatch in information retrieval (IR) mainly aim at leveraging either the relational semantics provided by external resources or the distributional semantics, recently investigated by deep neural approaches. Guided by the intuition that the relational semantics might improve the effectiveness of deep neural approaches, we propose the Deep Semantic Resource Inference Model (DSRIM) that relies on: 1) a representation of raw-data that models the relational semantics of text by jointly considering objects and relations expressed in a knowledge resource, and 2) an end-to-end neural architecture that learns the query-document relevance by leveraging the distributional and relational semantics of documents and queries. The experimental evaluation carried out on two TREC datasets from TREC Terabyte and TREC CDS tracks relying respectively on WordNet and MeSH resources, indicates that our model outperforms state-of-the-art semantic and deep neural IR models.
Tasks	Information Retrieval
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04922v2
PDF	http://arxiv.org/pdf/1706.04922v2.pdf
PWC	https://paperswithcode.com/paper/dsrim-a-deep-neural-information-retrieval
Repo
Framework

Recovering Homography from Camera Captured Documents using Convolutional Neural Networks


Title	Recovering Homography from Camera Captured Documents using Convolutional Neural Networks
Authors	Syed Ammar Abbas, Sibt ul Hussain
Abstract	Removing perspective distortion from hand held camera captured document images is one of the primitive tasks in document analysis, but unfortunately, no such method exists that can reliably remove the perspective distortion from document images automatically. In this paper, we propose a convolutional neural network based method for recovering homography from hand-held camera captured documents. Our proposed method works independent of document’s underlying content and is trained end-to-end in a fully automatic way. Specifically, this paper makes following three contributions: Firstly, we introduce a large scale synthetic dataset for recovering homography from documents images captured under different geometric and photometric transformations; secondly, we show that a generic convolutional neural network based architecture can be successfully used for regressing the corners positions of documents captured under wild settings; thirdly, we show that L1 loss can be reliably used for corners regression. Our proposed method gives state-of-the-art performance on the tested datasets, and has potential to become an integral part of document analysis pipeline.
Tasks
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03524v1
PDF	http://arxiv.org/pdf/1709.03524v1.pdf
PWC	https://paperswithcode.com/paper/recovering-homography-from-camera-captured
Repo
Framework

A Real-Time Autonomous Highway Accident Detection Model Based on Big Data Processing and Computational Intelligence


Title	A Real-Time Autonomous Highway Accident Detection Model Based on Big Data Processing and Computational Intelligence
Authors	A. Murat Ozbayoglu, Gokhan Kucukayan, Erdogan Dogdu
Abstract	Due to increasing urban population and growing number of motor vehicles, traffic congestion is becoming a major problem of the 21st century. One of the main reasons behind traffic congestion is accidents which can not only result in casualties and losses for the participants, but also in wasted and lost time for the others that are stuck behind the wheels. Early detection of an accident can save lives, provides quicker road openings, hence decreases wasted time and resources, and increases efficiency. In this study, we propose a preliminary real-time autonomous accident-detection system based on computational intelligence techniques. Istanbul City traffic-flow data for the year 2015 from various sensor locations are populated using big data processing methodologies. The extracted features are then fed into a nearest neighbor model, a regression tree, and a feed-forward neural network model. For the output, the possibility of an occurrence of an accident is predicted. The results indicate that even though the number of false alarms dominates the real accident cases, the system can still provide useful information that can be used for status verification and early reaction to possible accidents.
Tasks
Published	2017-12-26
URL	http://arxiv.org/abs/1712.09227v1
PDF	http://arxiv.org/pdf/1712.09227v1.pdf
PWC	https://paperswithcode.com/paper/a-real-time-autonomous-highway-accident
Repo
Framework

Unimodal probability distributions for deep ordinal classification


Title	Unimodal probability distributions for deep ordinal classification
Authors	Christopher Beckham, Christopher Pal
Abstract	Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. We evaluate this approach in the context of deep learning on two large ordinal image datasets, obtaining promising results.
Tasks
Published	2017-05-15
URL	http://arxiv.org/abs/1705.05278v2
PDF	http://arxiv.org/pdf/1705.05278v2.pdf
PWC	https://paperswithcode.com/paper/unimodal-probability-distributions-for-deep
Repo
Framework

Robust and Fast Decoding of High-Capacity Color QR Codes for Mobile Applications


Title	Robust and Fast Decoding of High-Capacity Color QR Codes for Mobile Applications
Authors	Zhibo Yang, Huanle Xu, Jianyuan Deng, Chen Change Loy, Wing Cheong Lau
Abstract	The use of color in QR codes brings extra data capacity, but also inflicts tremendous challenges on the decoding process due to chromatic distortion, cross-channel color interference and illumination variation. Particularly, we further discover a new type of chromatic distortion in high-density color QR codes, cross-module color interference, caused by the high density which also makes the geometric distortion correction more challenging. To address these problems, we propose two approaches, namely, LSVM-CMI and QDA-CMI, which jointly model these different types of chromatic distortion. Extended from SVM and QDA, respectively, both LSVM-CMI and QDA-CMI optimize over a particular objective function to learn a color classifier. Furthermore, a robust geometric transformation method and several pipeline refinements are proposed to boost the decoding performance for mobile applications. We put forth and implement a framework for high-capacity color QR codes equipped with our methods, called HiQ. To evaluate the performance of HiQ, we collect a challenging large-scale color QR code dataset, CUHK-CQRC, which consists of 5390 high-density color QR code samples. The comparison with the baseline method [2] on CUHK-CQRC shows that HiQ at least outperforms [2] by 188% in decoding success rate and 60% in bit error rate. Our implementation of HiQ in iOS and Android also demonstrates the effectiveness of our framework in real-world applications.
Tasks
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06447v3
PDF	http://arxiv.org/pdf/1704.06447v3.pdf
PWC	https://paperswithcode.com/paper/robust-and-fast-decoding-of-high-capacity
Repo
Framework

A Controlled Set-Up Experiment to Establish Personalized Baselines for Real-Life Emotion Recognition


Title	A Controlled Set-Up Experiment to Establish Personalized Baselines for Real-Life Emotion Recognition
Authors	Varvara Kollia, Noureddine Tayebi
Abstract	We design, conduct and present the results of a highly personalized baseline emotion recognition experiment, which aims to set reliable ground-truth estimates for the subject’s emotional state for real-life prediction under similar conditions using a small number of physiological sensors. We also propose an adaptive stimuli-selection mechanism that would use the user’s feedback as guide for future stimuli selection in the controlled-setup experiment and generate optimal ground-truth personalized sessions systematically. Initial results are very promising (85% accuracy) and variable importance analysis shows that only a few features, which are easy-to-implement in portable devices, would suffice to predict the subject’s emotional state.
Tasks	Emotion Recognition
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06537v1
PDF	http://arxiv.org/pdf/1703.06537v1.pdf
PWC	https://paperswithcode.com/paper/a-controlled-set-up-experiment-to-establish
Repo
Framework

Inconsistent Node Flattening for Improving Top-down Hierarchical Classification


Title	Inconsistent Node Flattening for Improving Top-down Hierarchical Classification
Authors	Azad Naik, Huzefa Rangwala
Abstract	Large-scale classification of data where classes are structurally organized in a hierarchy is an important area of research. Top-down approaches that exploit the hierarchy during the learning and prediction phase are efficient for large scale hierarchical classification. However, accuracy of top-down approaches is poor due to error propagation i.e., prediction errors made at higher levels in the hierarchy cannot be corrected at lower levels. One of the main reason behind errors at the higher levels is the presence of inconsistent nodes that are introduced due to the arbitrary process of creating these hierarchies by domain experts. In this paper, we propose two different data-driven approaches (local and global) for hierarchical structure modification that identifies and flattens inconsistent nodes present within the hierarchy. Our extensive empirical evaluation of the proposed approaches on several image and text datasets with varying distribution of features, classes and training instances per class shows improved classification performance over competing hierarchical modification approaches. Specifically, we see an improvement upto 7% in Macro-F1 score with our approach over best TD baseline. SOURCE CODE: http://www.cs.gmu.edu/~mlbio/InconsistentNodeFlattening
Tasks
Published	2017-06-05
URL	http://arxiv.org/abs/1706.01214v1
PDF	http://arxiv.org/pdf/1706.01214v1.pdf
PWC	https://paperswithcode.com/paper/inconsistent-node-flattening-for-improving
Repo
Framework

Efficient Algorithms for Moral Lineage Tracing


Title	Efficient Algorithms for Moral Lineage Tracing
Authors	Markus Rempfler, Jan-Hendrik Lange, Florian Jug, Corinna Blasse, Eugene W. Myers, Bjoern H. Menze, Bjoern Andres
Abstract	Lineage tracing, the joint segmentation and tracking of living cells as they move and divide in a sequence of light microscopy images, is a challenging task. Jug et al. have proposed a mathematical abstraction of this task, the moral lineage tracing problem (MLTP), whose feasible solutions define both a segmentation of every image and a lineage forest of cells. Their branch-and-cut algorithm, however, is prone to many cuts and slow convergence for large instances. To address this problem, we make three contributions: (i) we devise the first efficient primal feasible local search algorithms for the MLTP, (ii) we improve the branch-and-cut algorithm by separating tighter cutting planes and by incorporating our primal algorithms, (iii) we show in experiments that our algorithms find accurate solutions on the problem instances of Jug et al. and scale to larger instances, leveraging moral lineage tracing to practical significance.
Tasks
Published	2017-02-14
URL	http://arxiv.org/abs/1702.04111v2
PDF	http://arxiv.org/pdf/1702.04111v2.pdf
PWC	https://paperswithcode.com/paper/efficient-algorithms-for-moral-lineage
Repo
Framework

The Boolean Solution Problem from the Perspective of Predicate Logic - Extended Version


Title	The Boolean Solution Problem from the Perspective of Predicate Logic - Extended Version
Authors	Christoph Wernhard
Abstract	Finding solution values for unknowns in Boolean equations was a principal reasoning mode in the Algebra of Logic of the 19th century. Schr"oder investigated it as “Aufl"osungsproblem” (“solution problem”). It is closely related to the modern notion of Boolean unification. Today it is commonly presented in an algebraic setting, but seems potentially useful also in knowledge representation based on predicate logic. We show that it can be modeled on the basis of first-order logic extended by second-order quantification. A wealth of classical results transfers, foundations for algorithms unfold, and connections with second-order quantifier elimination and Craig interpolation show up. Although for first-order inputs the set of solutions is recursively enumerable, the development of constructive methods remains a challenge. We identify some cases that allow constructions, most of them based on Craig interpolation, and show a method to take vocabulary restrictions on solution components into account.
Tasks
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08329v3
PDF	http://arxiv.org/pdf/1706.08329v3.pdf
PWC	https://paperswithcode.com/paper/the-boolean-solution-problem-from-the
Repo
Framework

Neural Component Analysis for Fault Detection


Title	Neural Component Analysis for Fault Detection
Authors	Haitao Zhao
Abstract	Principal component analysis (PCA) is largely adopted for chemical process monitoring and numerous PCA-based systems have been developed to solve various fault detection and diagnosis problems. Since PCA-based methods assume that the monitored process is linear, nonlinear PCA models, such as autoencoder models and kernel principal component analysis (KPCA), has been proposed and applied to nonlinear process monitoring. However, KPCA-based methods need to perform eigen-decomposition (ED) on the kernel Gram matrix whose dimensions depend on the number of training data. Moreover, prefixed kernel parameters cannot be most effective for different faults which may need different parameters to maximize their respective detection performances. Autoencoder models lack the consideration of orthogonal constraints which is crucial for PCA-based algorithms. To address these problems, this paper proposes a novel nonlinear method, called neural component analysis (NCA), which intends to train a feedforward neural work with orthogonal constraints such as those used in PCA. NCA can adaptively learn its parameters through backpropagation and the dimensionality of the nonlinear features has no relationship with the number of training samples. Extensive experimental results on the Tennessee Eastman (TE) benchmark process show the superiority of NCA in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of NCA can be found in https://github.com/haitaozhao/Neural-Component-Analysis.git.
Tasks	Fault Detection
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04118v1
PDF	http://arxiv.org/pdf/1712.04118v1.pdf
PWC	https://paperswithcode.com/paper/neural-component-analysis-for-fault-detection
Repo
Framework

A Random Finite Set Model for Data Clustering


Title	A Random Finite Set Model for Data Clustering
Authors	Dinh Phung, Ba-Ngu Bo
Abstract	The goal of data clustering is to partition data points into groups to minimize a given objective function. While most existing clustering algorithms treat each data point as vector, in many applications each datum is not a vector but a point pattern or a set of points. Moreover, many existing clustering methods require the user to specify the number of clusters, which is not available in advance. This paper proposes a new class of models for data clustering that addresses set-valued data as well as unknown number of clusters, using a Dirichlet Process mixture of Poisson random finite sets. We also develop an efficient Markov Chain Monte Carlo posterior inference technique that can learn the number of clusters and mixture parameters automatically from the data. Numerical studies are presented to demonstrate the salient features of this new model, in particular its capacity to discover extremely unbalanced clusters in data.
Tasks
Published	2017-03-14
URL	http://arxiv.org/abs/1703.04832v1
PDF	http://arxiv.org/pdf/1703.04832v1.pdf
PWC	https://paperswithcode.com/paper/a-random-finite-set-model-for-data-clustering
Repo
Framework

Learning Linear Feature Space Transformations in Symbolic Regression


Title	Learning Linear Feature Space Transformations in Symbolic Regression
Authors	Jan Žegklitz, Petr Pošík
Abstract	We propose a new type of leaf node for use in Symbolic Regression (SR) that performs linear combinations of feature variables (LCF). These nodes can be handled in three different modes – an unsynchronized mode, where all LCFs are free to change on their own, a synchronized mode, where LCFs are sorted into groups in which they are forced to be identical throughout the whole individual, and a globally synchronized mode, which is similar to the previous mode but the grouping is done across the whole population. We also present two methods of evolving the weights of the LCFs – a purely stochastic way via mutation and a gradient-based way based on the backpropagation algorithm known from neural networks – and also a combination of both. We experimentally evaluate all configurations of LCFs in Multi-Gene Genetic Programming (MGGP), which was chosen as baseline, on a number of benchmarks. According to the results, we identified two configurations which increase the performance of the algorithm.
Tasks
Published	2017-04-17
URL	http://arxiv.org/abs/1704.05134v2
PDF	http://arxiv.org/pdf/1704.05134v2.pdf
PWC	https://paperswithcode.com/paper/learning-linear-feature-space-transformations
Repo
Framework

AJILE Movement Prediction: Multimodal Deep Learning for Natural Human Neural Recordings and Video


Title	AJILE Movement Prediction: Multimodal Deep Learning for Natural Human Neural Recordings and Video
Authors	Nancy Xin Ru Wang, Ali Farhadi, Rajesh Rao, Bingni Brunton
Abstract	Developing useful interfaces between brains and machines is a grand challenge of neuroengineering. An effective interface has the capacity to not only interpret neural signals, but predict the intentions of the human to perform an action in the near future; prediction is made even more challenging outside well-controlled laboratory experiments. This paper describes our approach to detect and to predict natural human arm movements in the future, a key challenge in brain computer interfacing that has never before been attempted. We introduce the novel Annotated Joints in Long-term ECoG (AJILE) dataset; AJILE includes automatically annotated poses of 7 upper body joints for four human subjects over 670 total hours (more than 72 million frames), along with the corresponding simultaneously acquired intracranial neural recordings. The size and scope of AJILE greatly exceeds all previous datasets with movements and electrocorticography (ECoG), making it possible to take a deep learning approach to movement prediction. We propose a multimodal model that combines deep convolutional neural networks (CNN) with long short-term memory (LSTM) blocks, leveraging both ECoG and video modalities. We demonstrate that our models are able to detect movements and predict future movements up to 800 msec before movement initiation. Further, our multimodal movement prediction models exhibit resilience to simulated ablation of input neural signals. We believe a multimodal approach to natural neural decoding that takes context into account is critical in advancing bioelectronic technologies and human neuroscience.
Tasks	Future prediction
Published	2017-09-13
URL	http://arxiv.org/abs/1709.05939v2
PDF	http://arxiv.org/pdf/1709.05939v2.pdf
PWC	https://paperswithcode.com/paper/ajile-movement-prediction-multimodal-deep
Repo
Framework