Paper Group ANR 108
Metacognitive Learning Approach for Online Tool Condition Monitoring. A Lightweight Approach for On-the-Fly Reflectance Estimation. FoveaNet: Perspective-aware Urban Scene Parsing. Fast Low-Rank Bayesian Matrix Completion with Hierarchical Gaussian Prior Models. On Seeking Consensus Between Document Similarity Measures. Kernel Method for Detecting …
Metacognitive Learning Approach for Online Tool Condition Monitoring
| Title | Metacognitive Learning Approach for Online Tool Condition Monitoring |
| Authors | Mahardhika Pratama, Eric Dimla, Chow Yin Lai, Edwin Lughofer |
| Abstract | As manufacturing processes become increasingly automated, so should tool condition monitoring (TCM) as it is impractical to have human workers monitor the state of the tools continuously. Tool condition is crucial to ensure the good quality of products: Worn tools affect not only the surface quality but also the dimensional accuracy, which means higher reject rate of the products. Therefore, there is an urgent need to identify tool failures before it occurs on the fly. While various versions of intelligent tool condition monitoring have been proposed, most of them suffer from a cognitive nature of traditional machine learning algorithms. They focus on the how to learn process without paying attention to other two crucial issues: what to learn, and when to learn. The what to learn and the when to learn provide self regulating mechanisms to select the training samples and to determine time instants to train a model. A novel tool condition monitoring approach based on a psychologically plausible concept, namely the metacognitive scaffolding theory, is proposed and built upon a recently published algorithm, recurrent classifier (rClass). The learning process consists of three phases: what to learn, how to learn, when to learn and makes use of a generalized recurrent network structure as a cognitive component. Experimental studies with real-world manufacturing data streams were conducted where rClass demonstrated the highest accuracy while retaining the lowest complexity over its counterparts. |
| Tasks | |
| Published | 2017-05-06 |
| URL | http://arxiv.org/abs/1705.02477v1 |
| http://arxiv.org/pdf/1705.02477v1.pdf | |
| PWC | https://paperswithcode.com/paper/metacognitive-learning-approach-for-online |
| Repo | |
| Framework | |
A Lightweight Approach for On-the-Fly Reflectance Estimation
| Title | A Lightweight Approach for On-the-Fly Reflectance Estimation |
| Authors | Kihwan Kim, Jinwei Gu, Stephen Tyree, Pavlo Molchanov, Matthias Nießner, Jan Kautz |
| Abstract | Estimating surface reflectance (BRDF) is one key component for complete 3D scene capture, with wide applications in virtual reality, augmented reality, and human computer interaction. Prior work is either limited to controlled environments (\eg gonioreflectometers, light stages, or multi-camera domes), or requires the joint optimization of shape, illumination, and reflectance, which is often computationally too expensive (\eg hours of running time) for real-time applications. Moreover, most prior work requires HDR images as input which further complicates the capture process. In this paper, we propose a lightweight approach for surface reflectance estimation directly from $8$-bit RGB images in real-time, which can be easily plugged into any 3D scanning-and-fusion system with a commodity RGBD sensor. Our method is learning-based, with an inference time of less than 90ms per scene and a model size of less than 340K bytes. We propose two novel network architectures, HemiCNN and Grouplet, to deal with the unstructured input data from multiple viewpoints under unknown illumination. We further design a loss function to resolve the color-constancy and scale ambiguity. In addition, we have created a large synthetic dataset, SynBRDF, which comprises a total of $500$K RGBD images rendered with a physically-based ray tracer under a variety of natural illumination, covering $5000$ materials and $5000$ shapes. SynBRDF is the first large-scale benchmark dataset for reflectance estimation. Experiments on both synthetic data and real data show that the proposed method effectively recovers surface reflectance, and outperforms prior work for reflectance estimation in uncontrolled environments. |
| Tasks | Color Constancy |
| Published | 2017-05-19 |
| URL | http://arxiv.org/abs/1705.07162v2 |
| http://arxiv.org/pdf/1705.07162v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-lightweight-approach-for-on-the-fly |
| Repo | |
| Framework | |
FoveaNet: Perspective-aware Urban Scene Parsing
| Title | FoveaNet: Perspective-aware Urban Scene Parsing |
| Authors | Xin Li, Zequn Jie, Wei Wang, Changsong Liu, Jimei Yang, Xiaohui Shen, Zhe Lin, Qiang Chen, Shuicheng Yan, Jiashi Feng |
| Abstract | Parsing urban scene images benefits many applications, especially self-driving. Most of the current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors. In this work, we propose a new FoveaNet model to fully exploit the perspective geometry of scene images and address the common failures of generic parsing models. FoveaNet estimates the perspective geometry of a scene image through a convolutional network which integrates supportive evidence from contextual objects within the image. Based on the perspective geometry information, FoveaNet “undoes” the camera perspective projection analyzing regions in the space of the actual scene, and thus provides much more reliable parsing results. Furthermore, to effectively address the recognition errors, FoveaNet introduces a new dense CRFs model that takes the perspective geometry as a prior potential. We evaluate FoveaNet on two urban scene parsing datasets, Cityspaces and CamVid, which demonstrates that FoveaNet can outperform all the well-established baselines and provide new state-of-the-art performance. |
| Tasks | Scene Parsing |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.02421v1 |
| http://arxiv.org/pdf/1708.02421v1.pdf | |
| PWC | https://paperswithcode.com/paper/foveanet-perspective-aware-urban-scene |
| Repo | |
| Framework | |
Fast Low-Rank Bayesian Matrix Completion with Hierarchical Gaussian Prior Models
| Title | Fast Low-Rank Bayesian Matrix Completion with Hierarchical Gaussian Prior Models |
| Authors | Linxiao Yang, Jun Fang, Huiping Duan, Hongbin Li, Bing Zeng |
| Abstract | The problem of low rank matrix completion is considered in this paper. To exploit the underlying low-rank structure of the data matrix, we propose a hierarchical Gaussian prior model, where columns of the low-rank matrix are assumed to follow a Gaussian distribution with zero mean and a common precision matrix, and a Wishart distribution is specified as a hyperprior over the precision matrix. We show that such a hierarchical Gaussian prior has the potential to encourage a low-rank solution. Based on the proposed hierarchical prior model, a variational Bayesian method is developed for matrix completion, where the generalized approximate massage passing (GAMP) technique is embedded into the variational Bayesian inference in order to circumvent cumbersome matrix inverse operations. Simulation results show that our proposed method demonstrates superiority over existing state-of-the-art matrix completion methods. |
| Tasks | Bayesian Inference, Low-Rank Matrix Completion, Matrix Completion |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.02455v2 |
| http://arxiv.org/pdf/1708.02455v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-low-rank-bayesian-matrix-completion-with |
| Repo | |
| Framework | |
On Seeking Consensus Between Document Similarity Measures
| Title | On Seeking Consensus Between Document Similarity Measures |
| Authors | Mieczysław Kłopotek |
| Abstract | This paper investigates the application of consensus clustering and meta-clustering to the set of all possible partitions of a data set. We show that when using a “complement” of Rand Index as a measure of cluster similarity, the total-separation partition, putting each element in a separate set, is chosen. |
| Tasks | |
| Published | 2017-02-13 |
| URL | http://arxiv.org/abs/1702.03724v1 |
| http://arxiv.org/pdf/1702.03724v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-seeking-consensus-between-document |
| Repo | |
| Framework | |
Kernel Method for Detecting Higher Order Interactions in multi-view Data: An Application to Imaging, Genetics, and Epigenetics
| Title | Kernel Method for Detecting Higher Order Interactions in multi-view Data: An Application to Imaging, Genetics, and Epigenetics |
| Authors | Md. Ashad Alam, Hui-Yi Lin, Vince Calhoun, Yu-Ping Wang |
| Abstract | In this study, we tested the interaction effect of multimodal datasets using a novel method called the kernel method for detecting higher order interactions among biologically relevant mulit-view data. Using a semiparametric method on a reproducing kernel Hilbert space (RKHS), we used a standard mixed-effects linear model and derived a score-based variance component statistic that tests for higher order interactions between multi-view data. The proposed method offers an intangible framework for the identification of higher order interaction effects (e.g., three way interaction) between genetics, brain imaging, and epigenetic data. Extensive numerical simulation studies were first conducted to evaluate the performance of this method. Finally, this method was evaluated using data from the Mind Clinical Imaging Consortium (MCIC) including single nucleotide polymorphism (SNP) data, functional magnetic resonance imaging (fMRI) scans, and deoxyribonucleic acid (DNA) methylation data, respectfully, in schizophrenia patients and healthy controls. We treated each gene-derived SNPs, region of interest (ROI) and gene-derived DNA methylation as a single testing unit, which are combined into triplets for evaluation. In addition, cardiovascular disease risk factors such as age, gender, and body mass index were assessed as covariates on hippocampal volume and compared between triplets. Our method identified $13$-triplets ($p$-values $\leq 0.001$) that included $6$ gene-derived SNPs, $10$ ROIs, and $6$ gene-derived DNA methylations that correlated with changes in hippocampal volume, suggesting that these triplets may be important in explaining schizophrenia-related neurodegeneration. With strong evidence ($p$-values $\leq 0.000001$), the triplet ({\bf MAGI2, CRBLCrus1.L, FBXO28}) has the potential to distinguish schizophrenia patients from the healthy control variations. |
| Tasks | |
| Published | 2017-07-14 |
| URL | http://arxiv.org/abs/1707.04368v1 |
| http://arxiv.org/pdf/1707.04368v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-method-for-detecting-higher-order |
| Repo | |
| Framework | |
Full-info Training for Deep Speaker Feature Learning
| Title | Full-info Training for Deep Speaker Feature Learning |
| Authors | Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng |
| Abstract | In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model. By enforcing the model to discriminate the speakers in the training data, frame-level speaker features can be derived from the last hidden layer. In spite of its good performance, a potential problem of the present model is that it involves a parametric classifier, i.e., the last affine layer, which may consume some discriminative knowledge, thus leading to `information leak’ for the feature learning. This paper presents a full-info training approach that discards the parametric classifier and enforces all the discriminative knowledge learned by the feature net. Our experiments on the Fisher database demonstrate that this new training scheme can produce more coherent features, leading to consistent and notable performance improvement on the speaker verification task. | |
| Tasks | Speaker Verification |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00366v3 |
| http://arxiv.org/pdf/1711.00366v3.pdf | |
| PWC | https://paperswithcode.com/paper/full-info-training-for-deep-speaker-feature |
| Repo | |
| Framework | |
Accurate 3D Reconstruction of Dynamic Scenes from Monocular Image Sequences with Severe Occlusions
| Title | Accurate 3D Reconstruction of Dynamic Scenes from Monocular Image Sequences with Severe Occlusions |
| Authors | Vladislav Golyanik, Torben Fetzer, Didier Stricker |
| Abstract | The paper introduces an accurate solution to dense orthographic Non-Rigid Structure from Motion (NRSfM) in scenarios with severe occlusions or, likewise, inaccurate correspondences. We integrate a shape prior term into variational optimisation framework. It allows to penalize irregularities of the time-varying structure on the per-pixel level if correspondence quality indicator such as an occlusion tensor is available. We make a realistic assumption that several non-occluded views of the scene are sufficient to estimate an initial shape prior, though the entire observed scene may exhibit non-rigid deformations. Experiments on synthetic and real image data show that the proposed framework significantly outperforms state of the art methods for correspondence establishment in combination with the state of the art NRSfM methods. Together with the profound insights into optimisation methods, implementation details for heterogeneous platforms are provided. |
| Tasks | 3D Reconstruction |
| Published | 2017-12-20 |
| URL | http://arxiv.org/abs/1712.07472v1 |
| http://arxiv.org/pdf/1712.07472v1.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-3d-reconstruction-of-dynamic-scenes |
| Repo | |
| Framework | |
Unsupervised Motion Artifact Detection in Wrist-Measured Electrodermal Activity Data
| Title | Unsupervised Motion Artifact Detection in Wrist-Measured Electrodermal Activity Data |
| Authors | Yuning Zhang, Maysam Haghdan, Kevin S. Xu |
| Abstract | One of the main benefits of a wrist-worn computer is its ability to collect a variety of physiological data in a minimally intrusive manner. Among these data, electrodermal activity (EDA) is readily collected and provides a window into a person’s emotional and sympathetic responses. EDA data collected using a wearable wristband are easily influenced by motion artifacts (MAs) that may significantly distort the data and degrade the quality of analyses performed on the data if not identified and removed. Prior work has demonstrated that MAs can be successfully detected using supervised machine learning algorithms on a small data set collected in a lab setting. In this paper, we demonstrate that unsupervised learning algorithms perform competitively with supervised algorithms for detecting MAs on EDA data collected in both a lab-based setting and a real-world setting comprising about 23 hours of data. We also find, somewhat surprisingly, that incorporating accelerometer data as well as EDA improves detection accuracy only slightly for supervised algorithms and significantly degrades the accuracy of unsupervised algorithms. |
| Tasks | |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08287v1 |
| http://arxiv.org/pdf/1707.08287v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-motion-artifact-detection-in |
| Repo | |
| Framework | |
RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process
| Title | RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process |
| Authors | Pavel Filonov, Fedor Kitashov, Andrey Lavrentyev |
| Abstract | An RNN-based forecasting approach is used to early detect anomalies in industrial multivariate time series data from a simulated Tennessee Eastman Process (TEP) with many cyber-attacks. This work continues a previously proposed LSTM-based approach to the fault detection in simpler data. It is considered necessary to adapt the RNN network to deal with data containing stochastic, stationary, transitive and a rich variety of anomalous behaviours. There is particular focus on early detection with special NAB-metric. A comparison with the DPCA approach is provided. The generated data set is made publicly available. |
| Tasks | Cyber Attack Detection, Fault Detection, Time Series |
| Published | 2017-09-07 |
| URL | http://arxiv.org/abs/1709.02232v1 |
| http://arxiv.org/pdf/1709.02232v1.pdf | |
| PWC | https://paperswithcode.com/paper/rnn-based-early-cyber-attack-detection-for |
| Repo | |
| Framework | |
Dynamic Tensor Clustering
| Title | Dynamic Tensor Clustering |
| Authors | Will Wei Sun, Lexin Li |
| Abstract | Dynamic tensor data are becoming prevalent in numerous applications. Existing tensor clustering methods either fail to account for the dynamic nature of the data, or are inapplicable to a general-order tensor. Also there is often a gap between statistical guarantee and computational efficiency for existing tensor clustering solutions. In this article, we aim to bridge this gap by proposing a new dynamic tensor clustering method, which takes into account both sparsity and fusion structures, and enjoys strong statistical guarantees as well as high computational efficiency. Our proposal is based upon a new structured tensor factorization that encourages both sparsity and smoothness in parameters along the specified tensor modes. Computationally, we develop a highly efficient optimization algorithm that benefits from substantial dimension reduction. In theory, we first establish a non-asymptotic error bound for the estimator from the structured tensor factorization. Built upon this error bound, we then derive the rate of convergence of the estimated cluster centers, and show that the estimated clusters recover the true cluster structures with a high probability. Moreover, our proposed method can be naturally extended to co-clustering of multiple modes of the tensor data. The efficacy of our approach is illustrated via simulations and a brain dynamic functional connectivity analysis from an Autism spectrum disorder study. |
| Tasks | Dimensionality Reduction |
| Published | 2017-08-24 |
| URL | http://arxiv.org/abs/1708.07259v2 |
| http://arxiv.org/pdf/1708.07259v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-tensor-clustering |
| Repo | |
| Framework | |
A Bayesian algorithm for detecting identity matches and fraud in image databases
| Title | A Bayesian algorithm for detecting identity matches and fraud in image databases |
| Authors | Gaurav Thakur |
| Abstract | A statistical algorithm for categorizing different types of matches and fraud in image databases is presented. The approach is based on a generative model of a graph representing images and connections between pairs of identities, trained using properties of a matching algorithm between images. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06230v1 |
| http://arxiv.org/pdf/1706.06230v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-algorithm-for-detecting-identity |
| Repo | |
| Framework | |
Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
| Title | Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks |
| Authors | Vardaan Pahuja, Anirban Laha, Shachar Mirkin, Vikas Raykar, Lili Kotlerman, Guy Lev |
| Abstract | The stream of words produced by Automatic Speech Recognition (ASR) systems is typically devoid of punctuations and formatting. Most natural language processing applications expect segmented and well-formatted texts as input, which is not available in ASR output. This paper proposes a novel technique of jointly modeling multiple correlated tasks such as punctuation and capitalization using bidirectional recurrent neural networks, which leads to improved performance for each of these tasks. This method could be extended for joint modeling of any other correlated sequence labeling tasks. |
| Tasks | Speech Recognition |
| Published | 2017-03-14 |
| URL | http://arxiv.org/abs/1703.04650v3 |
| http://arxiv.org/pdf/1703.04650v3.pdf | |
| PWC | https://paperswithcode.com/paper/joint-learning-of-correlated-sequence |
| Repo | |
| Framework | |
Causes and Corrections for Bimodal Multipath Scanning with Structured Light
| Title | Causes and Corrections for Bimodal Multipath Scanning with Structured Light |
| Authors | Yu Zhang, Daniel L. Lau, Ying Yu |
| Abstract | Structured light illumination is an active 3-D scanning technique based on projecting/capturing a set of striped patterns and measuring the warping of the patterns as they reflect off a target object’s surface. As designed, each pixel in the camera sees exactly one pixel from the projector; however, there are exceptions to this when the scanned surface has a complicated geometry with step edges and other discontinuities in depth or where the target surface has specularities that reflect light away from the camera. These situations are generally referred to multipath where a given camera pixel receives light from multiple positions from the projector. In the case of bimodal multipath, the camera pixel receives light from exactly two positions from the projector which occurs when light bounce back from a reflective surface or along a step edge where the edge slices through a pixel so that the pixel sees both a foreground and background surface. In this paper, we present a general mathematical model and address the bimodal multipath issue in a phase measuring profilometry scanner to measure the constructive and destructive interference between the two light paths, and by taking advantage of this interesting cue, separate the paths and make two separated depth measurements. We also validate our algorithm with both simulation and a number of challenging real cases. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02715v1 |
| http://arxiv.org/pdf/1706.02715v1.pdf | |
| PWC | https://paperswithcode.com/paper/causes-and-corrections-for-bimodal-multipath |
| Repo | |
| Framework | |
Learning Pairwise Disjoint Simple Languages from Positive Examples
| Title | Learning Pairwise Disjoint Simple Languages from Positive Examples |
| Authors | Alexis Linard, Rick Smetsers, Frits Vaandrager, Umar Waqas, Joost van Pinxten, Sicco Verwer |
| Abstract | A classical problem in grammatical inference is to identify a deterministic finite automaton (DFA) from a set of positive and negative examples. In this paper, we address the related - yet seemingly novel - problem of identifying a set of DFAs from examples that belong to different unknown simple regular languages. We propose two methods based on compression for clustering the observed positive examples. We apply our methods to a set of print jobs submitted to large industrial printers. |
| Tasks | |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01663v1 |
| http://arxiv.org/pdf/1706.01663v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-pairwise-disjoint-simple-languages |
| Repo | |
| Framework | |
