July 27, 2019

3241 words 16 mins read

Paper Group ANR 605

AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild. The ratio of normalizing constants for Bayesian graphical Gaussian model selection. The Bag Semantics of Ontology-Based Data Access. Accurate Inference for Adaptive Linear Models. Optimization of Ensemble Supervised Learning Algorithms for Increased Sensitivity …

AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild


Title	AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
Authors	Ali Mollahosseini, Behzad Hasani, Mohammad H. Mahoor
Abstract	Automated affective computing in the wild setting is a challenging problem in computer vision. Existing annotated databases of facial expressions in the wild are small and mostly cover discrete emotions (aka the categorical model). There are very limited annotated facial databases for affective computing in the continuous dimensional model (e.g., valence and arousal). To meet this need, we collected, annotated, and prepared for public distribution a new database of facial emotions in the wild (called AffectNet). AffectNet contains more than 1,000,000 facial images from the Internet by querying three major search engines using 1250 emotion related keywords in six different languages. About half of the retrieved images were manually annotated for the presence of seven discrete facial expressions and the intensity of valence and arousal. AffectNet is by far the largest database of facial expression, valence, and arousal in the wild enabling research in automated facial expression recognition in two different emotion models. Two baseline deep neural networks are used to classify images in the categorical model and predict the intensity of valence and arousal. Various evaluation metrics show that our deep neural network baselines can perform better than conventional machine learning methods and off-the-shelf facial expression recognition systems.
Tasks	Facial Expression Recognition
Published	2017-08-14
URL	http://arxiv.org/abs/1708.03985v4
PDF	http://arxiv.org/pdf/1708.03985v4.pdf
PWC	https://paperswithcode.com/paper/affectnet-a-database-for-facial-expression
Repo
Framework

The ratio of normalizing constants for Bayesian graphical Gaussian model selection


Title	The ratio of normalizing constants for Bayesian graphical Gaussian model selection
Authors	Gerard Letac, Helene Massam, Reza Mohammadi
Abstract	Many graphical Gaussian selection methods in a Bayesian framework use the G-Wishart as the conjugate prior on the precision matrix. The Bayes factor to compare a model governed by a graph G and a model governed by the neighboring graph G-e, derived from G by deleting an edge e, is a function of the ratios of prior and posterior normalizing constants of the G-Wishart for G and G-e. While more recent methods avoid the computation of the posterior ratio, computing the ratio of prior normalizing constants, (2) below, has remained a computational stumbling block. In this paper, we propose an explicit analytic approximation to (2) which is equal to the ratio of two Gamma functions evaluated at (delta+d)/2 and (delta+d+1)/2 respectively, where delta is the shape parameter of the G-Wishart and d is the number of paths of length two between the endpoints of e. This approximation allows us to avoid Monte Carlo methods, is computationally inexpensive and is scalable to high-dimensional problems. We show that the ratio of the approximation to the true value is always between zero and one and so, one cannot incur wild errors. In the particular case where the paths between the endpoints of e are disjoint, we show that the approximation is very good. When the paths between these two endpoints are not disjoint we give a sufficient condition for the approximation to be good. Numerical results show that the ratio of the approximation to the true value of the prior ratio is always between .55 and 1 and very often close to 1. We compare the results obtained with a model search using our approximation and a search using the double Metropolis-Hastings algorithm to compute the prior ratio. The results are extremely close.
Tasks	Model Selection
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04416v2
PDF	http://arxiv.org/pdf/1706.04416v2.pdf
PWC	https://paperswithcode.com/paper/the-ratio-of-normalizing-constants-for
Repo
Framework

The Bag Semantics of Ontology-Based Data Access


Title	The Bag Semantics of Ontology-Based Data Access
Authors	Charalampos Nikolaou, Egor V. Kostylev, George Konstantinidis, Mark Kaminski, Bernardo Cuenca Grau, Ian Horrocks
Abstract	Ontology-based data access (OBDA) is a popular approach for integrating and querying multiple data sources by means of a shared ontology. The ontology is linked to the sources using mappings, which assign views over the data to ontology predicates. Motivated by the need for OBDA systems supporting database-style aggregate queries, we propose a bag semantics for OBDA, where duplicate tuples in the views defined by the mappings are retained, as is the case in standard databases. We show that bag semantics makes conjunctive query answering in OBDA coNP-hard in data complexity. To regain tractability, we consider a rather general class of queries and show its rewritability to a generalisation of the relational calculus to bags.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07105v1
PDF	http://arxiv.org/pdf/1705.07105v1.pdf
PWC	https://paperswithcode.com/paper/the-bag-semantics-of-ontology-based-data
Repo
Framework

Accurate Inference for Adaptive Linear Models


Title	Accurate Inference for Adaptive Linear Models
Authors	Yash Deshpande, Lester Mackey, Vasilis Syrgkanis, Matt Taddy
Abstract	Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method – $\mathbf{W}$-decorrelation – for transforming the bias of adaptive linear regression estimators into variance. The method uses only coarse-grained information about the data collection policy and does not need access to propensity scores or exact knowledge of the policy. We bound the finite-sample bias and variance of the $\mathbf{W}$-estimator and develop asymptotically correct confidence intervals based on a novel martingale central limit theorem. We then demonstrate the empirical benefits of the generic $\mathbf{W}$-decorrelation procedure in two different adaptive data settings: the multi-armed bandit and the autoregressive time series.
Tasks	Time Series
Published	2017-12-18
URL	https://arxiv.org/abs/1712.06695v5
PDF	https://arxiv.org/pdf/1712.06695v5.pdf
PWC	https://paperswithcode.com/paper/accurate-inference-for-adaptive-linear-models
Repo
Framework

Optimization of Ensemble Supervised Learning Algorithms for Increased Sensitivity, Specificity, and AUC of Population-Based Colorectal Cancer Screenings


Title	Optimization of Ensemble Supervised Learning Algorithms for Increased Sensitivity, Specificity, and AUC of Population-Based Colorectal Cancer Screenings
Authors	Anirudh Kamath, Aditya Singh, Raj Ramnani, Ayush Vyas, Jay Shenoy
Abstract	Over 150,000 new people in the United States are diagnosed with colorectal cancer each year. Nearly a third die from it (American Cancer Society). The only approved noninvasive diagnosis tools currently involve fecal blood count tests (FOBTs) or stool DNA tests. Fecal blood count tests take only five minutes and are available over the counter for as low as $15. They are highly specific, yet not nearly as sensitive, yielding a high percentage (25%) of false negatives (Colon Cancer Alliance). Moreover, FOBT results are far too generalized, meaning that a positive result could mean much more than just colorectal cancer, and could just as easily mean hemorrhoids, anal fissure, proctitis, Crohn’s disease, diverticulosis, ulcerative colitis, rectal ulcer, rectal prolapse, ischemic colitis, angiodysplasia, rectal trauma, proctitis from radiation therapy, and others. Stool DNA tests, the modern benchmark for CRC screening, have a much higher sensitivity and specificity, but also cost $600, take two weeks to process, and are not for high-risk individuals or people with a history of polyps. To yield a cheap and effective CRC screening alternative, a unique ensemble-based classification algorithm is put in place that considers the FIT result, BMI, smoking history, and diabetic status of patients. This method is tested under ten-fold cross validation to have a .95 AUC, 92% specificity, 89% sensitivity, .88 F1, and 90% precision. Once clinically validated, this test promises to be cheaper, faster, and potentially more accurate when compared to a stool DNA test.
Tasks
Published	2017-08-13
URL	http://arxiv.org/abs/1708.03951v2
PDF	http://arxiv.org/pdf/1708.03951v2.pdf
PWC	https://paperswithcode.com/paper/optimization-of-ensemble-supervised-learning
Repo
Framework

Multi-Kernel LS-SVM Based Bio-Clinical Data Integration: Applications to Ovarian Cancer


Title	Multi-Kernel LS-SVM Based Bio-Clinical Data Integration: Applications to Ovarian Cancer
Authors	Jaya Thomas, Lee Sael
Abstract	The medical research facilitates to acquire a diverse type of data from the same individual for particular cancer. Recent studies show that utilizing such diverse data results in more accurate predictions. The major challenge faced is how to utilize such diverse data sets in an effective way. In this paper, we introduce a multiple kernel based pipeline for integrative analysis of high-throughput molecular data (somatic mutation, copy number alteration, DNA methylation and mRNA) and clinical data. We apply the pipeline on Ovarian cancer data from TCGA. After multiple kernels have been generated from the weighted sum of individual kernels, it is used to stratify patients and predict clinical outcomes. We examine the survival time, vital status, and neoplasm cancer status of each subtype to verify how well they cluster. We have also examined the power of molecular and clinical data in predicting dichotomized overall survival data and to classify the tumor grade for the cancer samples. It was observed that the integration of various data types yields higher log-rank statistics value. We were also able to predict clinical status with higher accuracy as compared to using individual data types.
Tasks
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02846v2
PDF	http://arxiv.org/pdf/1704.02846v2.pdf
PWC	https://paperswithcode.com/paper/multi-kernel-ls-svm-based-bio-clinical-data
Repo
Framework

SalProp: Salient object proposals via aggregated edge cues


Title	SalProp: Salient object proposals via aggregated edge cues
Authors	Prerana Mukherjee, Brejesh Lall, Sarvaswa Tandon
Abstract	In this paper, we propose a novel object proposal generation scheme by formulating a graph-based salient edge classification framework that utilizes the edge context. In the proposed method, we construct a Bayesian probabilistic edge map to assign a saliency value to the edgelets by exploiting low level edge features. A Conditional Random Field is then learned to effectively combine these features for edge classification with object/non-object label. We propose an objectness score for the generated windows by analyzing the salient edge density inside the bounding box. Extensive experiments on PASCAL VOC 2007 dataset demonstrate that the proposed method gives competitive performance against 10 popular generic object detection techniques while using fewer number of proposals.
Tasks	Object Detection, Object Proposal Generation
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04472v1
PDF	http://arxiv.org/pdf/1706.04472v1.pdf
PWC	https://paperswithcode.com/paper/salprop-salient-object-proposals-via
Repo
Framework

Object proposal generation applying the distance dependent Chinese restaurant process


Title	Object proposal generation applying the distance dependent Chinese restaurant process
Authors	Mikko Lauri, Simone Frintrop
Abstract	In application domains such as robotics, it is useful to represent the uncertainty related to the robot’s belief about the state of its environment. Algorithms that only yield a single “best guess” as a result are not sufficient. In this paper, we propose object proposal generation based on non-parametric Bayesian inference that allows quantification of the likelihood of the proposals. We apply Markov chain Monte Carlo to draw samples of image segmentations via the distance dependent Chinese restaurant process. Our method achieves state-of-the-art performance on an indoor object discovery data set, while additionally providing a likelihood term for each proposal. We show that the likelihood term can effectively be used to rank proposals according to their quality.
Tasks	Bayesian Inference, Object Proposal Generation
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03706v1
PDF	http://arxiv.org/pdf/1704.03706v1.pdf
PWC	https://paperswithcode.com/paper/object-proposal-generation-applying-the
Repo
Framework

Modularized Morphing of Neural Networks


Title	Modularized Morphing of Neural Networks
Authors	Tao Wei, Changhu Wang, Chang Wen Chen
Abstract	In this work we study the problem of network morphism, an effective learning scheme to morph a well-trained neural network to a new one with the network function completely preserved. Different from existing work where basic morphing types on the layer level were addressed, we target at the central problem of network morphism at a higher level, i.e., how a convolutional layer can be morphed into an arbitrary module of a neural network. To simplify the representation of a network, we abstract a module as a graph with blobs as vertices and convolutional layers as edges, based on which the morphing process is able to be formulated as a graph transformation problem. Two atomic morphing operations are introduced to compose the graphs, based on which modules are classified into two families, i.e., simple morphable modules and complex modules. We present practical morphing solutions for both of these two families, and prove that any reasonable module can be morphed from a single convolutional layer. Extensive experiments have been conducted based on the state-of-the-art ResNet on benchmark datasets, and the effectiveness of the proposed solution has been verified.
Tasks
Published	2017-01-12
URL	http://arxiv.org/abs/1701.03281v1
PDF	http://arxiv.org/pdf/1701.03281v1.pdf
PWC	https://paperswithcode.com/paper/modularized-morphing-of-neural-networks
Repo
Framework

Interest-Driven Discovery of Local Process Models


Title	Interest-Driven Discovery of Local Process Models
Authors	Niek Tax, Benjamin Dalmas, Natalia Sidorova, Wil M P van der Aalst, Sylvie Norre
Abstract	Local Process Models (LPM) describe structured fragments of process behavior occurring in the context of less structured business processes. Traditional LPM discovery aims to generate a collection of process models that describe highly frequent behavior, but these models do not always provide useful answers for questions posed by process analysts aiming at business process improvement. We propose a framework for goal-driven LPM discovery, based on utility functions and constraints. We describe four scopes on which these utility functions and constrains can be defined, and show that utility functions and constraints on different scopes can be combined to form composite utility functions/constraints. Finally, we demonstrate the applicability of our approach by presenting several actionable business insights discovered with LPM discovery on two real life data sets.
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07116v1
PDF	http://arxiv.org/pdf/1703.07116v1.pdf
PWC	https://paperswithcode.com/paper/interest-driven-discovery-of-local-process
Repo
Framework

Recurrent Estimation of Distributions


Title	Recurrent Estimation of Distributions
Authors	Junier B. Oliva, Kumar Avinava Dubey, Barnabas Poczos, Eric Xing, Jeff Schneider
Abstract	This paper presents the recurrent estimation of distributions (RED) for modeling real-valued data in a semiparametric fashion. RED models make two novel uses of recurrent neural networks (RNNs) for density estimation of general real-valued data. First, RNNs are used to transform input covariates into a latent space to better capture conditional dependencies in inputs. After, an RNN is used to compute the conditional distributions of the latent covariates. The resulting model is efficient to train, compute, and sample from, whilst producing normalized pdfs. The effectiveness of RED is shown via several real-world data experiments. Our results show that RED models achieve a lower held-out negative log-likelihood than other neural network approaches across multiple dataset sizes and dimensionalities. Further context of the efficacy of RED is provided by considering anomaly detection tasks, where we also observe better performance over alternative models.
Tasks	Anomaly Detection, Density Estimation
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10750v1
PDF	http://arxiv.org/pdf/1705.10750v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-estimation-of-distributions
Repo
Framework

Video and Accelerometer-Based Motion Analysis for Automated Surgical Skills Assessment


Title	Video and Accelerometer-Based Motion Analysis for Automated Surgical Skills Assessment
Authors	Aneeq Zia, Yachna Sharma, Vinay Bettadapura, Eric L. Sarin, Irfan Essa
Abstract	Purpose: Basic surgical skills of suturing and knot tying are an essential part of medical training. Having an automated system for surgical skills assessment could help save experts time and improve training efficiency. There have been some recent attempts at automated surgical skills assessment using either video analysis or acceleration data. In this paper, we present a novel approach for automated assessment of OSATS based surgical skills and provide an analysis of different features on multi-modal data (video and accelerometer data). Methods: We conduct the largest study, to the best of our knowledge, for basic surgical skills assessment on a dataset that contained video and accelerometer data for suturing and knot-tying tasks. We introduce “entropy based” features - Approximate Entropy (ApEn) and Cross-Approximate Entropy (XApEn), which quantify the amount of predictability and regularity of fluctuations in time-series data. The proposed features are compared to existing methods of Sequential Motion Texture (SMT), Discrete Cosine Transform (DCT) and Discrete Fourier Transform (DFT), for surgical skills assessment. Results: We report average performance of different features across all applicable OSATS criteria for suturing and knot tying tasks. Our analysis shows that the proposed entropy based features out-perform previous state-of-the-art methods using video data. For accelerometer data, our method performs better for suturing only. We also show that fusion of video and acceleration features can improve overall performance with the proposed entropy features achieving highest accuracy. Conclusions: Automated surgical skills assessment can be achieved with high accuracy using the proposed entropy features. Such a system can significantly improve the efficiency of surgical training in medical schools and teaching hospitals.
Tasks	Time Series
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07772v1
PDF	http://arxiv.org/pdf/1702.07772v1.pdf
PWC	https://paperswithcode.com/paper/video-and-accelerometer-based-motion-analysis
Repo
Framework

Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition


Title	Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition
Authors	Minju Jung, Haanvid Lee, Jun Tani
Abstract	Based on the progress of image recognition, video recognition has been extensively studied recently. However, most of the existing methods are focused on short-term but not long-term video recognition, called contextual video recognition. To address contextual video recognition, we use convolutional recurrent neural networks (ConvRNNs) having a rich spatio-temporal information processing capability, but ConvRNNs requires extensive computation that slows down training. In this paper, inspired by the normalization and detrending methods, we propose adaptive detrending (AD) for temporal normalization in order to accelerate the training of ConvRNNs, especially for convolutional gated recurrent unit (ConvGRU). AD removes internal covariate shift within a sequence of each neuron in recurrent neural networks (RNNs) by subtracting a trend. In the experiments for contextual recognition on ConvGRU, the results show that (1) ConvGRU clearly outperforms the feed-forward neural networks, (2) AD consistently offers a significant training acceleration and generalization improvement, and (3) AD is further improved by collaborating with the existing normalization methods.
Tasks	Video Recognition
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08764v1
PDF	http://arxiv.org/pdf/1705.08764v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-detrending-to-accelerate
Repo
Framework

Path planning for Robotic Mobile Fulfillment Systems


Title	Path planning for Robotic Mobile Fulfillment Systems
Authors	Marius Merschformann, Lin Xie, Daniel Erdmann
Abstract	This paper presents a collection of path planning algorithms for real-time movement of multiple robots across a Robotic Mobile Fulfillment System (RMFS). Robots are assigned to move storage units to pickers at working stations instead of requiring pickers to go to the storage area. Path planning algorithms aim to find paths for the robots to fulfill the requests without collisions or deadlocks. The state-of-the-art path planning algorithms, including WHCA*, FAR, BCP, OD&ID and CBS, were adapted to suit path planning in RMFS and integrated within a simulation tool to guide the robots from their starting points to their destinations during the storage and retrieval processes. Ten different layouts with a variety of numbers of robots, floors, pods, stations and the sizes of storage areas were considered in the simulation study. Performance metrics of throughput, path length and search time were monitored. Simulation results demonstrate the best algorithm based on each performance metric.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09347v2
PDF	http://arxiv.org/pdf/1706.09347v2.pdf
PWC	https://paperswithcode.com/paper/path-planning-for-robotic-mobile-fulfillment
Repo
Framework

Bounding and Counting Linear Regions of Deep Neural Networks


Title	Bounding and Counting Linear Regions of Deep Neural Networks
Authors	Thiago Serra, Christian Tjandraatmadja, Srikumar Ramalingam
Abstract	We investigate the complexity of deep neural networks (DNN) that represent piecewise linear (PWL) functions. In particular, we study the number of linear regions, i.e. pieces, that a PWL function represented by a DNN can attain, both theoretically and empirically. We present (i) tighter upper and lower bounds for the maximum number of linear regions on rectifier networks, which are exact for inputs of dimension one; (ii) a first upper bound for multi-layer maxout networks; and (iii) a first method to perform exact enumeration or counting of the number of regions by modeling the DNN with a mixed-integer linear formulation. These bounds come from leveraging the dimension of the space defining each linear region. The results also indicate that a deep rectifier network can only have more linear regions than every shallow counterpart with same number of neurons if that number exceeds the dimension of the input.
Tasks
Published	2017-11-06
URL	http://arxiv.org/abs/1711.02114v4
PDF	http://arxiv.org/pdf/1711.02114v4.pdf
PWC	https://paperswithcode.com/paper/bounding-and-counting-linear-regions-of-deep
Repo
Framework