Paper Group ANR 61
Color Face Recognition using High-Dimension Quaternion-based Adaptive Representation. nuts-flow/ml: data pre-processing for deep learning. Global-Local Airborne Mapping (GLAM): Reconstructing a City from Aerial Videos. Conditional generation of multi-modal data using constrained embedding space mapping. A Data Science Approach to Understanding Resi …
Color Face Recognition using High-Dimension Quaternion-based Adaptive Representation
| Title | Color Face Recognition using High-Dimension Quaternion-based Adaptive Representation |
| Authors | Qingxiang Feng, Yicong Zhou |
| Abstract | Recently, quaternion collaborative representation-based classification (QCRC) and quaternion sparse representation-based classification (QSRC) have been proposed for color face recognition. They can obtain correlation information among different color channels. However, their performance is unstable in different conditions. For example, QSRC performs better than than QCRC on some situations but worse on other situations. To benefit from quaternion-based $e_2$-norm minimization in QCRC and quaternion-based $e_1$-norm minimization in QSRC, we propose the quaternion-based adaptive representation (QAR) that uses a quaternion-based $e_p$-norm minimization ($1 \le p \le 2$) for color face recognition. To obtain the high dimension correlation information among different color channels, we further propose the high-dimension quaternion-based adaptive representation (HD-QAR). The experimental results demonstrate that the proposed QAR and HD-QAR achieve better recognition rates than QCRC, QSRC and several state-of-the-art methods. |
| Tasks | Face Recognition, Sparse Representation-based Classification |
| Published | 2017-11-19 |
| URL | http://arxiv.org/abs/1712.01642v1 |
| http://arxiv.org/pdf/1712.01642v1.pdf | |
| PWC | https://paperswithcode.com/paper/color-face-recognition-using-high-dimension |
| Repo | |
| Framework | |
nuts-flow/ml: data pre-processing for deep learning
| Title | nuts-flow/ml: data pre-processing for deep learning |
| Authors | S. Maetschke, R. Tennakoon, C. Vecchiola, R. Garnavi |
| Abstract | Data preprocessing is a fundamental part of any machine learning application and frequently the most time-consuming aspect when developing a machine learning solution. Preprocessing for deep learning is characterized by pipelines that lazily load data and perform data transformation, augmentation, batching and logging. Many of these functions are common across applications but require different arrangements for training, testing or inference. Here we introduce a novel software framework named nuts-flow/ml that encapsulates common preprocessing operations as components, which can be flexibly arranged to rapidly construct efficient preprocessing pipelines for deep learning. |
| Tasks | |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06046v2 |
| http://arxiv.org/pdf/1708.06046v2.pdf | |
| PWC | https://paperswithcode.com/paper/nuts-flowml-data-pre-processing-for-deep |
| Repo | |
| Framework | |
Global-Local Airborne Mapping (GLAM): Reconstructing a City from Aerial Videos
| Title | Global-Local Airborne Mapping (GLAM): Reconstructing a City from Aerial Videos |
| Authors | Hasnain Vohra, Maxim Bazik, Matthew Antone, Joseph Mundy, William Stephenson |
| Abstract | Monocular visual SLAM has become an attractive practical approach for robot localization and 3D environment mapping, since cameras are small, lightweight, inexpensive, and produce high-rate, high-resolution data streams. Although numerous robust tools have been developed, most existing systems are designed to operate in terrestrial environments and at relatively small scale (a few thousand frames) due to constraints on computation and storage. In this paper, we present a feature-based visual SLAM system for aerial video whose simple design permits near real-time operation, and whose scalability permits large-area mapping using tens of thousands of frames, all on a single conventional computer. Our approach consists of two parallel threads: the first incrementally creates small locally consistent submaps and estimates camera poses at video rate; the second aligns these submaps with one another to produce a single globally consistent map via factor graph optimization over both poses and landmarks. Scale drift is minimized through the use of 7-degree-of-freedom similarity transformations during submap alignment. We quantify our system’s performance on both simulated and real data sets, and demonstrate city-scale map reconstruction accurate to within 2 meters using nearly 90,000 aerial video frames - to our knowledge, the largest and fastest such reconstruction to date. |
| Tasks | |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01580v2 |
| http://arxiv.org/pdf/1706.01580v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-local-airborne-mapping-glam |
| Repo | |
| Framework | |
Conditional generation of multi-modal data using constrained embedding space mapping
| Title | Conditional generation of multi-modal data using constrained embedding space mapping |
| Authors | Subhajit Chaudhury, Sakyasingha Dasgupta, Asim Munawar, Md. A. Salam Khan, Ryuki Tachibana |
| Abstract | We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them. The embedding specific to a modality is first extracted and subsequently a constrained optimization procedure is performed to project the two embedding spaces to a common manifold. The individual embeddings are generated back from this common latent space. However, in order to enable independent conditional inference for separately extracting the corresponding embeddings from the common latent space representation, we deploy a proxy variable trick - wherein, the single shared latent space is replaced by the respective separate latent spaces of each modality. We design an objective function, such that, during training we can force these separate spaces to lie close to each other, by minimizing the distance between their probability distribution functions. Experimental results demonstrate that the learned joint model can generalize to learning concepts of double MNIST digits with additional attributes of colors,from both textual and speech input. |
| Tasks | |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.00860v2 |
| http://arxiv.org/pdf/1707.00860v2.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-generation-of-multi-modal-data |
| Repo | |
| Framework | |
A Data Science Approach to Understanding Residential Water Contamination in Flint
| Title | A Data Science Approach to Understanding Residential Water Contamination in Flint |
| Authors | Alex Chojnacki, Chengyu Dai, Arya Farahi, Guangsha Shi, Jared Webb, Daniel T. Zhang, Jacob Abernethy, Eric Schwartz |
| Abstract | When the residents of Flint learned that lead had contaminated their water system, the local government made water-testing kits available to them free of charge. The city government published the results of these tests, creating a valuable dataset that is key to understanding the causes and extent of the lead contamination event in Flint. This is the nation’s largest dataset on lead in a municipal water system. In this paper, we predict the lead contamination for each household’s water supply, and we study several related aspects of Flint’s water troubles, many of which generalize well beyond this one city. For example, we show that elevated lead risks can be (weakly) predicted from observable home attributes. Then we explore the factors associated with elevated lead. These risk assessments were developed in part via a crowd sourced prediction challenge at the University of Michigan. To inform Flint residents of these assessments, they have been incorporated into a web and mobile application funded by \texttt{Google.org}. We also explore questions of self-selection in the residential testing program, examining which factors are linked to when and how frequently residents voluntarily sample their water. |
| Tasks | |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01591v1 |
| http://arxiv.org/pdf/1707.01591v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-data-science-approach-to-understanding |
| Repo | |
| Framework | |
Identification of non-linear behavior models with restricted or redundant data
| Title | Identification of non-linear behavior models with restricted or redundant data |
| Authors | S. Carbillet, V. Guicheret-Retel, F. Trivaudey, F. Richard, M. L. Boubakar |
| Abstract | This study presents a new strategy for the identification of material parameters in the case of restricted or redundant data, based on a hybrid approach combining a genetic algorithm and the Levenberg-Marquardt method. The proposed methodology consists essentially in a statistically based topological analysis of the search domain, after this one has been reduced by the analysis of the parameters ranges. This is used to identify the parameters of a model representing the behavior of damaged elastic, visco-elastic, plastic and visco-plastic composite laminates. Optimization of the experimental tests on tubular samples leads to the selective identification of these parameters. |
| Tasks | |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.00884v1 |
| http://arxiv.org/pdf/1707.00884v1.pdf | |
| PWC | https://paperswithcode.com/paper/identification-of-non-linear-behavior-models |
| Repo | |
| Framework | |
Differential Evolution and Bayesian Optimisation for Hyper-Parameter Selection in Mixed-Signal Neuromorphic Circuits Applied to UAV Obstacle Avoidance
| Title | Differential Evolution and Bayesian Optimisation for Hyper-Parameter Selection in Mixed-Signal Neuromorphic Circuits Applied to UAV Obstacle Avoidance |
| Authors | Llewyn Salt, David Howard, Giacomo Indiveri, Yulia Sandamirskaya |
| Abstract | The Lobula Giant Movement Detector (LGMD) is a an identified neuron of the locust that detects looming objects and triggers its escape responses. Understanding the neural principles and networks that lead to these fast and robust responses can lead to the design of efficient facilitate obstacle avoidance strategies in robotic applications. Here we present a neuromorphic spiking neural network model of the LGMD driven by the output of a neuromorphic Dynamic Vision Sensor (DVS), which has been optimised to produce robust and reliable responses in the face of the constraints and variability of its mixed signal analogue-digital circuits. As this LGMD model has many parameters, we use the Differential Evolution (DE) algorithm to optimise its parameter space. We also investigate the use of Self-Adaptive Differential Evolution (SADE) which has been shown to ameliorate the difficulties of finding appropriate input parameters for DE. We explore the use of two biological mechanisms: synaptic plasticity and membrane adaptivity in the LGMD. We apply DE and SADE to find parameters best suited for an obstacle avoidance system on an unmanned aerial vehicle (UAV), and show how it outperforms state-of-the-art Bayesian optimisation used for comparison. |
| Tasks | Bayesian Optimisation |
| Published | 2017-04-17 |
| URL | http://arxiv.org/abs/1704.04853v3 |
| http://arxiv.org/pdf/1704.04853v3.pdf | |
| PWC | https://paperswithcode.com/paper/differential-evolution-and-bayesian |
| Repo | |
| Framework | |
CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data
| Title | CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data |
| Authors | Chih-Chung Hsu, Chia-Wen Lin |
| Abstract | Given a large unlabeled set of images, how to efficiently and effectively group them into clusters based on extracted visual representations remains a challenging problem. To address this problem, we propose a convolutional neural network (CNN) to jointly solve clustering and representation learning in an iterative manner. In the proposed method, given an input image set, we first randomly pick k samples and extract their features as initial cluster centroids using the proposed CNN with an initial model pre-trained from the ImageNet dataset. Mini-batch k-means is then performed to assign cluster labels to individual input samples for a mini-batch of images randomly sampled from the input image set until all images are processed. Subsequently, the proposed CNN simultaneously updates the parameters of the proposed CNN and the centroids of image clusters iteratively based on stochastic gradient descent. We also proposed a feature drift compensation scheme to mitigate the drift error caused by feature mismatch in representation learning. Experimental results demonstrate the proposed method outperforms start-of-the-art clustering schemes in terms of accuracy and storage complexity on large-scale image sets containing millions of images. |
| Tasks | Representation Learning |
| Published | 2017-05-19 |
| URL | http://arxiv.org/abs/1705.07091v2 |
| http://arxiv.org/pdf/1705.07091v2.pdf | |
| PWC | https://paperswithcode.com/paper/cnn-based-joint-clustering-and-representation |
| Repo | |
| Framework | |
Automated Design using Neural Networks and Gradient Descent
| Title | Automated Design using Neural Networks and Gradient Descent |
| Authors | Oliver Hennigh |
| Abstract | We propose a novel method that makes use of deep neural networks and gradient decent to perform automated design on complex real world engineering tasks. Our approach works by training a neural network to mimic the fitness function of a design optimization task and then, using the differential nature of the neural network, perform gradient decent to maximize the fitness. We demonstrate this methods effectiveness by designing an optimized heat sink and both 2D and 3D airfoils that maximize the lift drag ratio under steady state flow conditions. We highlight that our method has two distinct benefits over other automated design approaches. First, evaluating the neural networks prediction of fitness can be orders of magnitude faster then simulating the system of interest. Second, using gradient decent allows the design space to be searched much more efficiently then other gradient free methods. These two strengths work together to overcome some of the current shortcomings of automated design. |
| Tasks | |
| Published | 2017-10-27 |
| URL | http://arxiv.org/abs/1710.10352v1 |
| http://arxiv.org/pdf/1710.10352v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-design-using-neural-networks-and |
| Repo | |
| Framework | |
Application of backpropagation neural networks to both stages of fingerprinting based WIPS
| Title | Application of backpropagation neural networks to both stages of fingerprinting based WIPS |
| Authors | Caifa Zhou, Andreas Wieser |
| Abstract | We propose a scheme to employ backpropagation neural networks (BPNNs) for both stages of fingerprinting-based indoor positioning using WLAN/WiFi signal strengths (FWIPS): radio map construction during the offline stage, and localization during the online stage. Given a training radio map (TRM), i.e., a set of coordinate vectors and associated WLAN/WiFi signal strengths of the available access points, a BPNN can be trained to output the expected signal strengths for any input position within the region of interest (BPNN-RM). This can be used to provide a continuous representation of the radio map and to filter, densify or decimate a discrete radio map. Correspondingly, the TRM can also be used to train another BPNN to output the expected position within the region of interest for any input vector of recorded signal strengths and thus carry out localization (BPNN-LA).Key aspects of the design of such artificial neural networks for a specific application are the selection of design parameters like the number of hidden layers and nodes within the network, and the training procedure. Summarizing extensive numerical simulations, based on real measurements in a testbed, we analyze the impact of these design choices on the performance of the BPNN and compare the results in particular to those obtained using the $k$ nearest neighbors ($k$NN) and weighted $k$ nearest neighbors approaches to FWIPS. |
| Tasks | |
| Published | 2017-03-14 |
| URL | http://arxiv.org/abs/1703.06912v1 |
| http://arxiv.org/pdf/1703.06912v1.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-backpropagation-neural |
| Repo | |
| Framework | |
Minimal Dependency Translation: a Framework for Computer-Assisted Translation for Under-Resourced Languages
| Title | Minimal Dependency Translation: a Framework for Computer-Assisted Translation for Under-Resourced Languages |
| Authors | Michael Gasser |
| Abstract | This paper introduces Minimal Dependency Translation (MDT), an ongoing project to develop a rule-based framework for the creation of rudimentary bilingual lexicon-grammars for machine translation and computer-assisted translation into and out of under-resourced languages as well as initial steps towards an implementation of MDT for English-to-Amharic translation. The basic units in MDT, called groups, are headed multi-item sequences. In addition to wordforms, groups may contain lexemes, syntactic-semantic categories, and grammatical features. Each group is associated with one or more translations, each of which is a group in a target language. During translation, constraint satisfaction is used to select a set of source-language groups for the input sentence and to sequence the words in the associated target-language groups. |
| Tasks | Machine Translation |
| Published | 2017-10-02 |
| URL | http://arxiv.org/abs/1710.00923v1 |
| http://arxiv.org/pdf/1710.00923v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimal-dependency-translation-a-framework |
| Repo | |
| Framework | |
Support vector machine and its bias correction in high-dimension, low-sample-size settings
| Title | Support vector machine and its bias correction in high-dimension, low-sample-size settings |
| Authors | Yugo Nakayama, Kazuyoshi Yata, Makoto Aoshima |
| Abstract | In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimension, low-sample-size (HDLSS) settings. We show that the hard-margin linear SVM holds a consistency property in which misclassification rates tend to zero as the dimension goes to infinity under certain severe conditions. We show that the SVM is very biased in HDLSS settings and its performance is affected by the bias directly. In order to overcome such difficulties, we propose a bias-corrected SVM (BC-SVM). We show that the BC-SVM gives preferable performances in HDLSS settings. We also discuss the SVMs in multiclass HDLSS settings. Finally, we check the performance of the classifiers in actual data analyses. |
| Tasks | |
| Published | 2017-02-26 |
| URL | http://arxiv.org/abs/1702.08019v1 |
| http://arxiv.org/pdf/1702.08019v1.pdf | |
| PWC | https://paperswithcode.com/paper/support-vector-machine-and-its-bias |
| Repo | |
| Framework | |
Visual Concepts and Compositional Voting
| Title | Visual Concepts and Compositional Voting |
| Authors | Jianyu Wang, Zhishuai Zhang, Cihang Xie, Yuyin Zhou, Vittal Premachandran, Jun Zhu, Lingxi Xie, Alan Yuille |
| Abstract | It is very attractive to formulate vision in terms of pattern theory \cite{Mumford2010pattern}, where patterns are defined hierarchically by compositions of elementary building blocks. But applying pattern theory to real world images is currently less successful than discriminative methods such as deep networks. Deep networks, however, are black-boxes which are hard to interpret and can easily be fooled by adding occluding objects. It is natural to wonder whether by better understanding deep networks we can extract building blocks which can be used to develop pattern theoretic models. This motivates us to study the internal representations of a deep network using vehicle images from the PASCAL3D+ dataset. We use clustering algorithms to study the population activities of the features and extract a set of visual concepts which we show are visually tight and correspond to semantic parts of vehicles. To analyze this we annotate these vehicles by their semantic parts to create a new dataset, VehicleSemanticParts, and evaluate visual concepts as unsupervised part detectors. We show that visual concepts perform fairly well but are outperformed by supervised discriminative methods such as Support Vector Machines (SVM). We next give a more detailed analysis of visual concepts and how they relate to semantic parts. Following this, we use the visual concepts as building blocks for a simple pattern theoretical model, which we call compositional voting. In this model several visual concepts combine to detect semantic parts. We show that this approach is significantly better than discriminative methods like SVM and deep networks trained specifically for semantic part detection. Finally, we return to studying occlusion by creating an annotated dataset with occlusion, called VehicleOcclusion, and show that compositional voting outperforms even deep networks when the amount of occlusion becomes large. |
| Tasks | |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04451v1 |
| http://arxiv.org/pdf/1711.04451v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-concepts-and-compositional-voting |
| Repo | |
| Framework | |
Semantic Similarity from Natural Language and Ontology Analysis
| Title | Semantic Similarity from Natural Language and Ontology Analysis |
| Authors | Sébastien Harispe, Sylvie Ranwez, Stefan Janaqi, Jacky Montmain |
| Abstract | Artificial Intelligence federates numerous scientific fields in the aim of developing machines able to assist human operators performing complex treatments – most of which demand high cognitive skills (e.g. learning or decision processes). Central to this quest is to give machines the ability to estimate the likeness or similarity between things in the way human beings estimate the similarity between stimuli. In this context, this book focuses on semantic measures: approaches designed for comparing semantic entities such as units of language, e.g. words, sentences, or concepts and instances defined into knowledge bases. The aim of these measures is to assess the similarity or relatedness of such semantic entities by taking into account their semantics, i.e. their meaning – intuitively, the words tea and coffee, which both refer to stimulating beverage, will be estimated to be more semantically similar than the words toffee (confection) and coffee, despite that the last pair has a higher syntactic similarity. The two state-of-the-art approaches for estimating and quantifying semantic similarities/relatedness of semantic entities are presented in detail: the first one relies on corpora analysis and is based on Natural Language Processing techniques and semantic models while the second is based on more or less formal, computer-readable and workable forms of knowledge such as semantic networks, thesaurus or ontologies. (…) Beyond a simple inventory and categorization of existing measures, the aim of this monograph is to convey novices as well as researchers of these domains towards a better understanding of semantic similarity estimation and more generally semantic measures. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05295v1 |
| http://arxiv.org/pdf/1704.05295v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-similarity-from-natural-language-and |
| Repo | |
| Framework | |
Challenges ahead Electron Microscopy for Structural Biology from the Image Processing point of view
| Title | Challenges ahead Electron Microscopy for Structural Biology from the Image Processing point of view |
| Authors | Carlos Oscar S. Sorzano, Jose Maria Carazo |
| Abstract | Since the introduction of Direct Electron Detectors (DEDs), the resolution and range of macromolecules amenable to this technique has significantly widened, generating a broad interest that explains the well over a dozen reviews in top journal in the last two years. Similarly, the number of job offers to lead EM groups and/or coordinate EM facilities has exploded, and FEI (the main microscope manufacturer for Life Sciences) has received more than 100 orders of high-end electron microscopes by summer 2016. Strategic corporate movements are also happening, with very big players entering the market through key acquisitions (Thermo Fisher has recently bought FEI for $4.2B), partly attracted by new Pharma interest in the field, now perceived to be in a position to impact structure-based drug design. The scientific perspectives are indeed extremely positive but, in these moments of well-founded generalized optimists, we want to make a reflection on some of the hurdles ahead us, since they certainly exist and they indeed limit the informational content of cryoEM projects. Here we focus on image processing aspects, particularly in the so-called area of Single Particle Analysis, discussing some of the current resolution and high-throughput limiting factors. |
| Tasks | |
| Published | 2017-01-02 |
| URL | http://arxiv.org/abs/1701.00326v1 |
| http://arxiv.org/pdf/1701.00326v1.pdf | |
| PWC | https://paperswithcode.com/paper/challenges-ahead-electron-microscopy-for |
| Repo | |
| Framework | |
