July 27, 2019

2893 words 14 mins read

Paper Group ANR 478

Mix-and-Match Tuning for Self-Supervised Semantic Segmentation. A Novel Data-Driven Framework for Risk Characterization and Prediction from Electronic Medical Records: A Case Study of Renal Failure. Denoising of image gradients and total generalized variation denoising. Gaussian Process Latent Force Models for Learning and Stochastic Control of Phy …

Mix-and-Match Tuning for Self-Supervised Semantic Segmentation


Title	Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
Authors	Xiaohang Zhan, Ziwei Liu, Ping Luo, Xiaoou Tang, Chen Change Loy
Abstract	Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g. ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently proposed to pre-train a network without any human-provided labels. The key of this new form of learning is to design a proxy task (e.g. image colorization), from which a discriminative loss can be formulated on unlabeled data. Many proxy tasks, however, lack the critical supervision signals that could induce discriminative representation for the target image segmentation task. Thus self-supervision’s performance is still far from that of supervised pre-training. In this study, we overcome this limitation by incorporating a “mix-and-match” (M&M) tuning stage in the self-supervision pipeline. The proposed approach is readily pluggable to many self-supervision methods and does not use more annotated samples than the original process. Yet, it is capable of boosting the performance of target image segmentation task to surpass fully-supervised pre-trained counterpart. The improvement is made possible by better harnessing the limited pixel-wise annotations in the target dataset. Specifically, we first introduce the “mix” stage, which sparsely samples and mixes patches from the target set to reflect rich and diverse local patch statistics of target images. A “match” stage then forms a class-wise connected graph, which can be used to derive a strong triplet-based discriminative loss for fine-tuning the network. Our paradigm follows the standard practice in existing self-supervised studies and no extra data or label is required. With the proposed M&M approach, for the first time, a self-supervision method can achieve comparable or even better performance compared to its ImageNet pre-trained counterpart on both PASCAL VOC2012 dataset and CityScapes dataset.
Tasks	Colorization, Semantic Segmentation
Published	2017-12-02
URL	http://arxiv.org/abs/1712.00661v3
PDF	http://arxiv.org/pdf/1712.00661v3.pdf
PWC	https://paperswithcode.com/paper/mix-and-match-tuning-for-self-supervised
Repo
Framework

A Novel Data-Driven Framework for Risk Characterization and Prediction from Electronic Medical Records: A Case Study of Renal Failure


Title	A Novel Data-Driven Framework for Risk Characterization and Prediction from Electronic Medical Records: A Case Study of Renal Failure
Authors	Prithwish Chakraborty, Vishrawas Gopalakrishnan, Sharon M. H. Alford, Faisal Farooq
Abstract	Electronic medical records (EMR) contain longitudinal information about patients that can be used to analyze outcomes. Typically, studies on EMR data have worked with established variables that have already been acknowledged to be associated with certain outcomes. However, EMR data may also contain hitherto unrecognized factors for risk association and prediction of outcomes for a disease. In this paper, we present a scalable data-driven framework to analyze EMR data corpus in a disease agnostic way that systematically uncovers important factors influencing outcomes in patients, as supported by data and without expert guidance. We validate the importance of such factors by using the framework to predict for the relevant outcomes. Specifically, we analyze EMR data covering approximately 47 million unique patients to characterize renal failure (RF) among type 2 diabetic (T2DM) patients. We propose a specialized L1 regularized Cox Proportional Hazards (CoxPH) survival model to identify the important factors from those available from patient encounter history. To validate the identified factors, we use a specialized generalized linear model (GLM) to predict the probability of renal failure for individual patients within a specified time window. Our experiments indicate that the factors identified via our data-driven method overlap with the patient characteristics recognized by experts. Our approach allows for scalable, repeatable and efficient utilization of data available in EMRs, confirms prior medical knowledge and can generate new hypothesis without expert supervision.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11022v1
PDF	http://arxiv.org/pdf/1711.11022v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-data-driven-framework-for-risk
Repo
Framework

Denoising of image gradients and total generalized variation denoising


Title	Denoising of image gradients and total generalized variation denoising
Authors	Birgit Komander, Dirk A. Lorenz, Lena Vestweber
Abstract	We revisit total variation denoising and study an augmented model where we assume that an estimate of the image gradient is available. We show that this increases the image reconstruction quality and derive that the resulting model resembles the total generalized variation denoising method, thus providing a new motivation for this model. Further, we propose to use a constraint denoising model and develop a variational denoising model that is basically parameter free, i.e. all model parameters are estimated directly from the noisy image. Moreover, we use Chambolle-Pock’s primal dual method as well as the Douglas-Rachford method for the new models. For the latter one has to solve large discretizations of partial differential equations. We propose to do this in an inexact manner using the preconditioned conjugate gradients method and derive preconditioners for this. Numerical experiments show that the resulting method has good denoising properties and also that preconditioning does increase convergence speed significantly. Finally we analyze the duality gap of different formulations of the TGV denoising problem and derive a simple stopping criterion.
Tasks	Denoising, Image Reconstruction
Published	2017-12-22
URL	http://arxiv.org/abs/1712.08585v3
PDF	http://arxiv.org/pdf/1712.08585v3.pdf
PWC	https://paperswithcode.com/paper/denoising-of-image-gradients-and-total
Repo
Framework

Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems


Title	Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems
Authors	Simo Särkkä, Mauricio A. Álvarez, Neil D. Lawrence
Abstract	This article is concerned with learning and stochastic control in physical systems which contain unknown input signals. These unknown signals are modeled as Gaussian processes (GP) with certain parametrized covariance structures. The resulting latent force models (LFMs) can be seen as hybrid models that contain a first-principles physical model part and a non-parametric GP model part. We briefly review the statistical inference and learning methods for this kind of models, introduce stochastic control methodology for the models, and provide new theoretical observability and controllability results for them.
Tasks	Gaussian Processes
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05409v2
PDF	http://arxiv.org/pdf/1709.05409v2.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-latent-force-models-for
Repo
Framework

Semi-Supervised Affective Meaning Lexicon Expansion Using Semantic and Distributed Word Representations


Title	Semi-Supervised Affective Meaning Lexicon Expansion Using Semantic and Distributed Word Representations
Authors	Areej Alhothali, Jesse Hoey
Abstract	In this paper, we propose an extension to graph-based sentiment lexicon induction methods by incorporating distributed and semantic word representations in building the similarity graph to expand a three-dimensional sentiment lexicon. We also implemented and evaluated the label propagation using four different word representations and similarity metrics. Our comprehensive evaluation of the four approaches was performed on a single data set, demonstrating that all four methods can generate a significant number of new sentiment assignments with high accuracy. The highest correlations (tau=0.51) and the lowest error (mean absolute error < 1.1%), obtained by combining both the semantic and the distributional features, outperformed the distributional-based and semantic-based label-propagation models and approached a supervised algorithm.
Tasks
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09825v1
PDF	http://arxiv.org/pdf/1703.09825v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-affective-meaning-lexicon
Repo
Framework

Deep Learning for Reliable Mobile Edge Analytics in Intelligent Transportation Systems


Title	Deep Learning for Reliable Mobile Edge Analytics in Intelligent Transportation Systems
Authors	Aidin Ferdowsi, Ursula Challita, Walid Saad
Abstract	Intelligent transportation systems (ITSs) will be a major component of tomorrow’s smart cities. However, realizing the true potential of ITSs requires ultra-low latency and reliable data analytics solutions that can combine, in real-time, a heterogeneous mix of data stemming from the ITS network and its environment. Such data analytics capabilities cannot be provided by conventional cloud-centric data processing techniques whose communication and computing latency can be high. Instead, edge-centric solutions that are tailored to the unique ITS environment must be developed. In this paper, an edge analytics architecture for ITSs is introduced in which data is processed at the vehicle or roadside smart sensor level in order to overcome the ITS latency and reliability challenges. With a higher capability of passengers’ mobile devices and intra-vehicle processors, such a distributed edge computing architecture can leverage deep learning techniques for reliable mobile sensing in ITSs. In this context, the ITS mobile edge analytics challenges pertaining to heterogeneous data, autonomous control, vehicular platoon control, and cyber-physical security are investigated. Then, different deep learning solutions for such challenges are proposed. The proposed deep learning solutions will enable ITS edge analytics by endowing the ITS devices with powerful computer vision and signal processing functions. Preliminary results show that the proposed edge analytics architecture, coupled with the power of deep learning algorithms, can provide a reliable, secure, and truly smart transportation environment.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04135v1
PDF	http://arxiv.org/pdf/1712.04135v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-reliable-mobile-edge
Repo
Framework

Topical Behavior Prediction from Massive Logs


Title	Topical Behavior Prediction from Massive Logs
Authors	Shih-Chieh Su
Abstract	In this paper, we study the topical behavior in a large scale. We use the network logs where each entry contains the entity ID, the timestamp, and the meta data about the activity. Both the temporal and the spatial relationships of the behavior are explored with the deep learning architectures combing the recurrent neural network (RNN) and the convolutional neural network (CNN). To make the behavioral data appropriate for the spatial learning in the CNN, we propose several reduction steps to form the topical metrics and to place them homogeneously like pixels in the images. The experimental result shows both temporal and spatial gains when compared against a multilayer perceptron (MLP) network. A new learning framework called the spatially connected convolutional networks (SCCN) is introduced to predict the topical metrics more efficiently.
Tasks
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03381v1
PDF	http://arxiv.org/pdf/1708.03381v1.pdf
PWC	https://paperswithcode.com/paper/topical-behavior-prediction-from-massive-logs
Repo
Framework

Summarizing First-Person Videos from Third Persons’ Points of Views


Title	Summarizing First-Person Videos from Third Persons’ Points of Views
Authors	Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang
Abstract	Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage. However, most existing studies rely on training data of third-person videos, which cannot easily generalize to highlight the first-person ones. With the goal of deriving an effective model to summarize first-person videos, we propose a novel deep neural network architecture for describing and discriminating vital spatiotemporal information across videos with different points of view. Our proposed model is realized in a semi-supervised setting, in which fully annotated third-person videos, unlabeled first-person videos, and a small number of annotated first-person ones are presented during training. In our experiments, qualitative and quantitative evaluations on both benchmarks and our collected first-person video datasets are presented.
Tasks
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08922v2
PDF	http://arxiv.org/pdf/1711.08922v2.pdf
PWC	https://paperswithcode.com/paper/summarizing-first-person-videos-from-third
Repo
Framework

Introspective Generative Modeling: Decide Discriminatively


Title	Introspective Generative Modeling: Decide Discriminatively
Authors	Justin Lazarow, Long Jin, Zhuowen Tu
Abstract	We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capable of introspection: being able to self-evaluate the difference between its generated samples and the given training data. When followed by repeated discriminative learning, desirable properties of modern discriminative classifiers are directly inherited by the generator. IGM learns a cascade of CNN classifiers using a synthesis-by-classification algorithm. In the experiments, we observe encouraging results on a number of applications including texture modeling, artistic style transferring, face modeling, and semi-supervised learning.
Tasks
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07820v1
PDF	http://arxiv.org/pdf/1704.07820v1.pdf
PWC	https://paperswithcode.com/paper/introspective-generative-modeling-decide
Repo
Framework

Autoencoder-augmented Neuroevolution for Visual Doom Playing


Title	Autoencoder-augmented Neuroevolution for Visual Doom Playing
Authors	Samuel Alvernaz, Julian Togelius
Abstract	Neuroevolution has proven effective at many reinforcement learning tasks, but does not seem to scale well to high-dimensional controller representations, which are needed for tasks where the input is raw pixel data. We propose a novel method where we train an autoencoder to create a comparatively low-dimensional representation of the environment observation, and then use CMA-ES to train neural network controllers acting on this input data. As the behavior of the agent changes the nature of the input data, the autoencoder training progresses throughout evolution. We test this method in the VizDoom environment built on the classic FPS Doom, where it performs well on a health-pack gathering task.
Tasks
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03902v1
PDF	http://arxiv.org/pdf/1707.03902v1.pdf
PWC	https://paperswithcode.com/paper/autoencoder-augmented-neuroevolution-for
Repo
Framework

Stochastic Constraint Programming as Reinforcement Learning


Title	Stochastic Constraint Programming as Reinforcement Learning
Authors	Steven Prestwich, Roberto Rossi, Armagan Tarim
Abstract	Stochastic Constraint Programming (SCP) is an extension of Constraint Programming (CP) used for modelling and solving problems involving constraints and uncertainty. SCP inherits excellent modelling abilities and filtering algorithms from CP, but so far it has not been applied to large problems. Reinforcement Learning (RL) extends Dynamic Programming to large stochastic problems, but is problem-specific and has no generic solvers. We propose a hybrid combining the scalability of RL with the modelling and constraint filtering methods of CP. We implement a prototype in a CP system and demonstrate its usefulness on SCP problems.
Tasks
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07183v1
PDF	http://arxiv.org/pdf/1704.07183v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-constraint-programming-as
Repo
Framework

Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric Approaches


Title	Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric Approaches
Authors	Wenshuo Wang, Junqiang Xi, Ding Zhao
Abstract	Analysis and recognition of driving styles are profoundly important to intelligent transportation and vehicle calibration. This paper presents a novel driving style analysis framework using the primitive driving patterns learned from naturalistic driving data. In order to achieve this, first, a Bayesian nonparametric learning method based on a hidden semi-Markov model (HSMM) is introduced to extract primitive driving patterns from time series driving data without prior knowledge of the number of these patterns. In the Bayesian nonparametric approach, we utilize a hierarchical Dirichlet process (HDP) instead of learning the unknown number of smooth dynamical modes of HSMM, thus generating the primitive driving patterns. Each primitive pattern is clustered and then labeled using behavioral semantics according to drivers’ physical and psychological perception thresholds. For each driver, 75 primitive driving patterns in car-following scenarios are learned and semantically labeled. In order to show the HDP-HSMM’s utility to learn primitive driving patterns, other two Bayesian nonparametric approaches, HDP-HMM and sticky HDP-HMM, are compared. The naturalistic driving data of 18 drivers were collected from the University of Michigan Safety Pilot Model Deployment (SPDM) database. The individual driving styles are discussed according to distribution characteristics of the learned primitive driving patterns and also the difference in driving styles among drivers are evaluated using the Kullback-Leibler divergence. The experiment results demonstrate that the proposed primitive pattern-based method can allow one to semantically understand driver behaviors and driving styles.
Tasks	Calibration, Time Series
Published	2017-08-16
URL	http://arxiv.org/abs/1708.08986v1
PDF	http://arxiv.org/pdf/1708.08986v1.pdf
PWC	https://paperswithcode.com/paper/driving-style-analysis-using-primitive
Repo
Framework

Learning Autoencoded Radon Projections


Title	Learning Autoencoded Radon Projections
Authors	Aditya Sriram, Shivam Kalra, H. R. Tizhoosh, Shahryar Rahnamayan
Abstract	Autoencoders have been recently used for encoding medical images. In this study, we design and validate a new framework for retrieving medical images by classifying Radon projections, compressed in the deepest layer of an autoencoder. As the autoencoder reduces the dimensionality, a multilayer perceptron (MLP) can be employed to classify the images. The integration of MLP promotes a rather shallow learning architecture which makes the training faster. We conducted a comparative study to examine the capabilities of autoencoders for different inputs such as raw images, Histogram of Oriented Gradients (HOG) and normalized Radon projections. Our framework is benchmarked on IRMA dataset containing $14,410$ x-ray images distributed across $57$ different classes. Experiments show an IRMA error of $313$ (equivalent to $\approx 82%$ accuracy) outperforming state-of-the-art works on retrieval from IRMA dataset using autoencoders.
Tasks
Published	2017-09-27
URL	http://arxiv.org/abs/1710.01247v1
PDF	http://arxiv.org/pdf/1710.01247v1.pdf
PWC	https://paperswithcode.com/paper/learning-autoencoded-radon-projections
Repo
Framework

Photometric Stereo by Hemispherical Metric Embedding


Title	Photometric Stereo by Hemispherical Metric Embedding
Authors	Ofer Bartal, Nati Ofir, Yaron Lipman, Ronen Basri
Abstract	Photometric Stereo methods seek to reconstruct the 3d shape of an object from motionless images obtained with varying illumination. Most existing methods solve a restricted problem where the physical reflectance model, such as Lambertian reflectance, is known in advance. In contrast, we do not restrict ourselves to a specific reflectance model. Instead, we offer a method that works on a wide variety of reflectances. Our approach uses a simple yet uncommonly used property of the problem - the sought after normals are points on a unit hemisphere. We present a novel embedding method that maps pixels to normals on the unit hemisphere. Our experiments demonstrate that this approach outperforms existing manifold learning methods for the task of hemisphere embedding. We further show successful reconstructions of objects from a wide variety of reflectances including smooth, rough, diffuse and specular surfaces, even in the presence of significant attached shadows. Finally, we empirically prove that under these challenging settings we obtain more accurate shape reconstructions than existing methods.
Tasks
Published	2017-06-25
URL	http://arxiv.org/abs/1706.08153v1
PDF	http://arxiv.org/pdf/1706.08153v1.pdf
PWC	https://paperswithcode.com/paper/photometric-stereo-by-hemispherical-metric
Repo
Framework

On Identifiability of Nonnegative Matrix Factorization


Title	On Identifiability of Nonnegative Matrix Factorization
Authors	Xiao Fu, Kejun Huang, Nicholas D. Sidiropoulos
Abstract	In this letter, we propose a new identification criterion that guarantees the recovery of the low-rank latent factors in the nonnegative matrix factorization (NMF) model, under mild conditions. Specifically, using the proposed criterion, it suffices to identify the latent factors if the rows of one factor are \emph{sufficiently scattered} over the nonnegative orthant, while no structural assumption is imposed on the other factor except being full-rank. This is by far the mildest condition under which the latent factors are provably identifiable from the NMF model.
Tasks
Published	2017-09-02
URL	http://arxiv.org/abs/1709.00614v1
PDF	http://arxiv.org/pdf/1709.00614v1.pdf
PWC	https://paperswithcode.com/paper/on-identifiability-of-nonnegative-matrix
Repo
Framework