July 26, 2019

3207 words 16 mins read

Paper Group ANR 797

Automated Linear-Time Detection and Quality Assessment of Superpixels in Uncalibrated True- or False-Color RGB Images. Semantically Consistent Image Completion with Fine-grained Details. Multi-Objective Approaches to Markov Decision Processes with Uncertain Transition Parameters. CS591 Report: Application of siamesa network in 2D transformation. A …

Automated Linear-Time Detection and Quality Assessment of Superpixels in Uncalibrated True- or False-Color RGB Images


Title	Automated Linear-Time Detection and Quality Assessment of Superpixels in Uncalibrated True- or False-Color RGB Images
Authors	Andrea Baraldi, Dirk Tiede, Stefan Lang
Abstract	Capable of automated near real time superpixel detection and quality assessment in an uncalibrated monitor typical red green blue (RGB) image, depicted in either true or false colors, an original low level computer vision (CV) lightweight computer program, called RGB Image Automatic Mapper (RGBIAM), is designed and implemented. Constrained by the Calibration Validation (CalVal) requirements of the Quality Assurance Framework for Earth Observation (QA4EO) guidelines, RGBIAM requires as mandatory an uncalibrated RGB image pre processing first stage, consisting of an automated statistical model based color constancy algorithm. The RGBIAM hybrid inference pipeline comprises: (I) a direct quantitative to nominal (QN) RGB variable transform, where RGB pixel values are mapped onto a prior dictionary of color names, equivalent to a static polyhedralization of the RGB cube. Prior color naming is the deductive counterpart of inductive vector quantization (VQ), whose typical VQ error function to minimize is a root mean square error (RMSE). In the output multi level color map domain, superpixels are automatically detected in linear time as connected sets of pixels featuring the same color label. (II) An inverse nominal to quantitative (NQ) RGB variable transform, where a superpixelwise constant RGB image approximation is generated in linear time to assess a VQ error image. The hybrid direct and inverse RGBIAM QNQ transform is: (i) general purpose, data and application independent. (ii) Automated, i.e., it requires no user machine interaction. (iii) Near real time, with a computational complexity increasing linearly with the image size. (iv) Implemented in tile streaming mode, to cope with massive images. Collected outcome and process quality indicators, including degree of automation, computational efficiency, VQ rate and VQ error, are consistent with theoretical expectations.
Tasks	Calibration, Color Constancy, Quantization
Published	2017-01-08
URL	http://arxiv.org/abs/1701.01940v1
PDF	http://arxiv.org/pdf/1701.01940v1.pdf
PWC	https://paperswithcode.com/paper/automated-linear-time-detection-and-quality
Repo
Framework

Semantically Consistent Image Completion with Fine-grained Details


Title	Semantically Consistent Image Completion with Fine-grained Details
Authors	Pengpeng Liu, Xiaojuan Qi, Pinjia He, Yikang Li, Michael R. Lyu, Irwin King
Abstract	Image completion has achieved significant progress due to advances in generative adversarial networks (GANs). Albeit natural-looking, the synthesized contents still lack details, especially for scenes with complex structures or images with large holes. This is because there exists a gap between low-level reconstruction loss and high-level adversarial loss. To address this issue, we introduce a perceptual network to provide mid-level guidance, which measures the semantical similarity between the synthesized and original contents in a similarity-enhanced space. We conduct a detailed analysis on the effects of different losses and different levels of perceptual features in image completion, showing that there exist complementarity between adversarial training and perceptual features. By combining them together, our model can achieve nearly seamless fusion results in an end-to-end manner. Moreover, we design an effective lightweight generator architecture, which can achieve effective image inpainting with far less parameters. Evaluated on CelebA Face and Paris StreetView dataset, our proposed method significantly outperforms existing methods.
Tasks	Image Inpainting
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09345v1
PDF	http://arxiv.org/pdf/1711.09345v1.pdf
PWC	https://paperswithcode.com/paper/semantically-consistent-image-completion-with
Repo
Framework

Multi-Objective Approaches to Markov Decision Processes with Uncertain Transition Parameters


Title	Multi-Objective Approaches to Markov Decision Processes with Uncertain Transition Parameters
Authors	Dimitri Scheftelowitsch, Peter Buchholz, Vahid Hashemi, Holger Hermanns
Abstract	Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not known precisely. Different types of MDPs with uncertain, imprecise or bounded transition rates or probabilities and rewards exist in the literature. Commonly, analysis of models with uncertainties amounts to searching for the most robust policy which means that the goal is to generate a policy with the greatest lower bound on performance (or, symmetrically, the lowest upper bound on costs). However, hedging against an unlikely worst case may lead to losses in other situations. In general, one is interested in policies that behave well in all situations which results in a multi-objective view on decision making. In this paper, we consider policies for the expected discounted reward measure of MDPs with uncertain parameters. In particular, the approach is defined for bounded-parameter MDPs (BMDPs) [8]. In this setting the worst, best and average case performances of a policy are analyzed simultaneously, which yields a multi-scenario multi-objective optimization problem. The paper presents and evaluates approaches to compute the pure Pareto optimal policies in the value vector space.
Tasks	Decision Making
Published	2017-10-20
URL	http://arxiv.org/abs/1710.08986v1
PDF	http://arxiv.org/pdf/1710.08986v1.pdf
PWC	https://paperswithcode.com/paper/multi-objective-approaches-to-markov-decision
Repo
Framework

CS591 Report: Application of siamesa network in 2D transformation


Title	CS591 Report: Application of siamesa network in 2D transformation
Authors	Dorothy Chang
Abstract	Deep learning has been extensively used various aspects of computer vision area. Deep learning separate itself from traditional neural network by having a much deeper and complicated network layers in its network structures. Traditionally, deep neural network is abundantly used in computer vision tasks including classification and detection and has achieve remarkable success and set up a new state of the art results in these fields. Instead of using neural network for vision recognition and detection. I will show the ability of neural network to do image registration, synthesis of images and image retrieval in this report.
Tasks	Image Registration, Image Retrieval
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09598v1
PDF	http://arxiv.org/pdf/1706.09598v1.pdf
PWC	https://paperswithcode.com/paper/cs591-report-application-of-siamesa-network
Repo
Framework

A Dictionary Approach to Identifying Transient RFI


Title	A Dictionary Approach to Identifying Transient RFI
Authors	Daniel Czech, Amit Mishra, Michael Inggs
Abstract	As radio telescopes become more sensitive, the damaging effects of radio frequency interference (RFI) become more apparent. Near radio telescope arrays, RFI sources are often easily removed or replaced; the challenge lies in identifying them. Transient (impulsive) RFI is particularly difficult to identify. We propose a novel dictionary-based approach to transient RFI identification. RFI events are treated as sequences of sub-events, drawn from particular labelled classes. We demonstrate an automated method of extracting and labelling sub-events using a dataset of transient RFI. A dictionary of labels may be used in conjunction with hidden Markov models to identify the sources of RFI events reliably. We attain improved classification accuracy over traditional approaches such as SVMs or a na"ive kNN classifier. Finally, we investigate why transient RFI is difficult to classify. We show that cluster separation in the principal components domain is influenced by the mains supply phase for certain sources.
Tasks
Published	2017-11-23
URL	http://arxiv.org/abs/1711.08823v1
PDF	http://arxiv.org/pdf/1711.08823v1.pdf
PWC	https://paperswithcode.com/paper/a-dictionary-approach-to-identifying
Repo
Framework

Pointed subspace approach to incomplete data


Title	Pointed subspace approach to incomplete data
Authors	Łukasz Struski, Marek Śmieja, Jacek Tabor
Abstract	Incomplete data are often represented as vectors with filled missing attributes joined with flag vectors indicating missing components. In this paper we generalize this approach and represent incomplete data as pointed affine subspaces. This allows to perform various affine transformations of data, as whitening or dimensionality reduction. We embed such generalized missing data into a vector space by mapping pointed affine subspace (generalized missing data point) to a vector containing imputed values joined with a corresponding projection matrix. Such an operation preserves the scalar product of the embedding defined for flag vectors and allows to input transformed incomplete data to typical classification methods.
Tasks	Dimensionality Reduction
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00840v1
PDF	http://arxiv.org/pdf/1705.00840v1.pdf
PWC	https://paperswithcode.com/paper/pointed-subspace-approach-to-incomplete-data
Repo
Framework

Model-Free Control of Thermostatically Controlled Loads Connected to a District Heating Network


Title	Model-Free Control of Thermostatically Controlled Loads Connected to a District Heating Network
Authors	Bert J. Claessens, Dirk Vanhoudt, Johan Desmedt, Frederik Ruelens
Abstract	Optimal control of thermostatically controlled loads connected to a district heating network is considered a sequential decision- making problem under uncertainty. The practicality of a direct model-based approach is compromised by two challenges, namely scalability due to the large dimensionality of the problem and the system identification required to identify an accurate model. To help in mitigating these problems, this paper leverages on recent developments in reinforcement learning in combination with a market-based multi-agent system to obtain a scalable solution that obtains a significant performance improvement in a practical learning time. The control approach is applied on a scenario comprising 100 thermostatically controlled loads connected to a radial district heating network supplied by a central combined heat and power plant. Both for an energy arbitrage and a peak shaving objective, the control approach requires 60 days to obtain a performance within 65% of a theoretical lower bound on the cost.
Tasks	Decision Making
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08074v2
PDF	http://arxiv.org/pdf/1701.08074v2.pdf
PWC	https://paperswithcode.com/paper/model-free-control-of-thermostatically
Repo
Framework

Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning


Title	Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
Authors	Nat Dilokthanakul, Christos Kaplanis, Nick Pawlowski, Murray Shanahan
Abstract	The problem of sparse rewards is one of the hardest challenges in contemporary reinforcement learning. Hierarchical reinforcement learning (HRL) tackles this problem by using a set of temporally-extended actions, or options, each of which has its own subgoal. These subgoals are normally handcrafted for specific tasks. Here, though, we introduce a generic class of subgoals with broad applicability in the visual domain. Underlying our approach (in common with work using “auxiliary tasks”) is the hypothesis that the ability to control aspects of the environment is an inherently useful skill to have. We incorporate such subgoals in an end-to-end hierarchical reinforcement learning system and test two variants of our algorithm on a number of games from the Atari suite. We highlight the advantage of our approach in one of the hardest games – Montezuma’s revenge – for which the ability to handle sparse rewards is key. Our agent learns several times faster than the current state-of-the-art HRL agent in this game, reaching a similar level of performance. UPDATE 22/11/17: We found that a standard A3C agent with a simple shaped reward, i.e. extrinsic reward + feature control intrinsic reward, has comparable performance to our agent in Montezuma Revenge. In light of the new experiments performed, the advantage of our HRL approach can be attributed more to its ability to learn useful features from intrinsic rewards rather than its ability to explore and reuse abstracted skills with hierarchical components. This has led us to a new conclusion about the result.
Tasks	Hierarchical Reinforcement Learning, Montezuma’s Revenge
Published	2017-05-18
URL	http://arxiv.org/abs/1705.06769v2
PDF	http://arxiv.org/pdf/1705.06769v2.pdf
PWC	https://paperswithcode.com/paper/feature-control-as-intrinsic-motivation-for
Repo
Framework

E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks


Title	E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks
Authors	Franyell Silfa, Gem Dot, Jose-Maria Arnau, Antonio Gonzalez
Abstract	Recurrent Neural Networks (RNNs) are a key technology for emerging applications such as automatic speech recognition, machine translation or image description. Long Short Term Memory (LSTM) networks are the most successful RNN implementation, as they can learn long term dependencies to achieve high accuracy. Unfortunately, the recurrent nature of LSTM networks significantly constrains the amount of parallelism and, hence, multicore CPUs and many-core GPUs exhibit poor efficiency for RNN inference. In this paper, we present E-PUR, an energy-efficient processing unit tailored to the requirements of LSTM computation. The main goal of E-PUR is to support large recurrent neural networks for low-power mobile devices. E-PUR provides an efficient hardware implementation of LSTM networks that is flexible to support diverse applications. One of its main novelties is a technique that we call Maximizing Weight Locality (MWL), which improves the temporal locality of the memory accesses for fetching the synaptic weights, reducing the memory requirements by a large extent. Our experimental results show that E-PUR achieves real-time performance for different LSTM networks, while reducing energy consumption by orders of magnitude with respect to general-purpose processors and GPUs, and it requires a very small chip area. Compared to a modern mobile SoC, an NVIDIA Tegra X1, E-PUR provides an average energy reduction of 92x.
Tasks	Machine Translation, Speech Recognition
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07480v1
PDF	http://arxiv.org/pdf/1711.07480v1.pdf
PWC	https://paperswithcode.com/paper/e-pur-an-energy-efficient-processing-unit-for
Repo
Framework

Bayesian Hypernetworks


Title	Bayesian Hypernetworks
Authors	David Krueger, Chin-Wei Huang, Riashat Islam, Ryan Turner, Alexandre Lacoste, Aaron Courville
Abstract	We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a simple noise distribution, $p(\vec\epsilon) = \N(\vec 0,\mat I)$, to a distribution $q(\pp) := q(h(\vec\epsilon))$ over the parameters $\pp$ of another neural network (the “primary network”)@. We train $q$ with variational inference, using an invertible $\h$ to enable efficient estimation of the variational lower bound on the posterior $p(\pp \D)$ via sampling. In contrast to most methods for Bayesian deep learning, Bayesian hypernets can represent a complex multimodal approximate posterior with correlations between parameters, while enabling cheap iid sampling of~$q(\pp)$. In practice, Bayesian hypernets can provide a better defense against adversarial examples than dropout, and also exhibit competitive performance on a suite of tasks which evaluate model uncertainty, including regularization, active learning, and anomaly detection.
Tasks	Active Learning, Anomaly Detection, Bayesian Inference
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04759v2
PDF	http://arxiv.org/pdf/1710.04759v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-hypernetworks
Repo
Framework

Denoising Gravitational Waves using Deep Learning with Recurrent Denoising Autoencoders


Title	Denoising Gravitational Waves using Deep Learning with Recurrent Denoising Autoencoders
Authors	Hongyu Shen, Daniel George, E. A. Huerta, Zhizhen Zhao
Abstract	Gravitational wave astronomy is a rapidly growing field of modern astrophysics, with observations being made frequently by the LIGO detectors. Gravitational wave signals are often extremely weak and the data from the detectors, such as LIGO, is contaminated with non-Gaussian and non-stationary noise, often containing transient disturbances which can obscure real signals. Traditional denoising methods, such as principal component analysis and dictionary learning, are not optimal for dealing with this non-Gaussian noise, especially for low signal-to-noise ratio gravitational wave signals. Furthermore, these methods are computationally expensive on large datasets. To overcome these issues, we apply state-of-the-art signal processing techniques, based on recent groundbreaking advancements in deep learning, to denoise gravitational wave signals embedded either in Gaussian noise or in real LIGO noise. We introduce SMTDAE, a Staired Multi-Timestep Denoising Autoencoder, based on sequence-to-sequence bi-directional Long-Short-Term-Memory recurrent neural networks. We demonstrate the advantages of using our unsupervised deep learning approach and show that, after training only using simulated Gaussian noise, SMTDAE achieves superior recovery performance for gravitational wave signals embedded in real non-Gaussian LIGO noise.
Tasks	Denoising, Dictionary Learning
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09919v1
PDF	http://arxiv.org/pdf/1711.09919v1.pdf
PWC	https://paperswithcode.com/paper/denoising-gravitational-waves-using-deep
Repo
Framework

Urban Scene Segmentation with Laser-Constrained CRFs


Title	Urban Scene Segmentation with Laser-Constrained CRFs
Authors	Charika De Alvis, Lionel Ott, Fabio Ramos
Abstract	Robots typically possess sensors of different modalities, such as colour cameras, inertial measurement units, and 3D laser scanners. Often, solving a particular problem becomes easier when more than one modality is used. However, while there are undeniable benefits to combine sensors of different modalities the process tends to be complicated. Segmenting scenes observed by the robot into a discrete set of classes is a central requirement for autonomy as understanding the scene is the first step to reason about future situations. Scene segmentation is commonly performed using either image data or 3D point cloud data. In computer vision many successful methods for scene segmentation are based on conditional random fields (CRF) where the maximum a posteriori (MAP) solution to the segmentation can be obtained by inference. In this paper we devise a new CRF inference method for scene segmentation that incorporates global constraints, enforcing the sets of nodes are assigned the same class label. To do this efficiently, the CRF is formulated as a relaxed quadratic program whose MAP solution is found using a gradient-based optimisation approach. The proposed method is evaluated on images and 3D point cloud data gathered in urban environments where image data provides the appearance features needed by the CRF, while the 3D point cloud data provides global spatial constraints over sets of nodes. Comparisons with belief propagation, conventional quadratic programming relaxation, and higher order potential CRF show the benefits of the proposed method.
Tasks	Scene Segmentation
Published	2017-01-07
URL	http://arxiv.org/abs/1701.01892v1
PDF	http://arxiv.org/pdf/1701.01892v1.pdf
PWC	https://paperswithcode.com/paper/urban-scene-segmentation-with-laser
Repo
Framework

Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points


Title	Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points
Authors	Dimitrios Tzionas, Abhilash Srikantha, Pablo Aponte, Juergen Gall
Abstract	Hand motion capture has been an active research topic in recent years, following the success of full-body pose tracking. Despite similarities, hand tracking proves to be more challenging, characterized by a higher dimensionality, severe occlusions and self-similarity between fingers. For this reason, most approaches rely on strong assumptions, like hands in isolation or expensive multi-camera systems, that limit the practical use. In this work, we propose a framework for hand tracking that can capture the motion of two interacting hands using only a single, inexpensive RGB-D camera. Our approach combines a generative model with collision detection and discriminatively learned salient points. We quantitatively evaluate our approach on 14 new sequences with challenging interactions.
Tasks	Motion Capture, Pose Tracking
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00515v1
PDF	http://arxiv.org/pdf/1704.00515v1.pdf
PWC	https://paperswithcode.com/paper/capturing-hand-motion-with-an-rgb-d-sensor
Repo
Framework

Simple Problems: The Simplicial Gluing Structure of Pareto Sets and Pareto Fronts


Title	Simple Problems: The Simplicial Gluing Structure of Pareto Sets and Pareto Fronts
Authors	Naoki Hamada
Abstract	Quite a few studies on real-world applications of multi-objective optimization reported that their Pareto sets and Pareto fronts form a topological simplex. Such a class of problems was recently named the simple problems, and their Pareto set and Pareto front were observed to have a gluing structure similar to the faces of a simplex. This paper gives a theoretical justification for that observation by proving the gluing structure of the Pareto sets/fronts of subproblems of a simple problem. The simplicity of standard benchmark problems is studied.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1709.10377v1
PDF	http://arxiv.org/pdf/1709.10377v1.pdf
PWC	https://paperswithcode.com/paper/simple-problems-the-simplicial-gluing
Repo
Framework

Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs


Title	Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs
Authors	Timo von Marcard, Bodo Rosenhahn, Michael J. Black, Gerard Pons-Moll
Abstract	We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body. Since the problem is heavily under-constrained, previous methods either use a large number of sensors, which is intrusive, or they require additional video input. We take a different approach and constrain the problem by: (i) making use of a realistic statistical body model that includes anthropometric constraints and (ii) using a joint optimization framework to fit the model to orientation and acceleration measurements over multiple frames. The resulting tracker Sparse Inertial Poser (SIP) enables 3D human pose estimation using only 6 sensors (attached to the wrists, lower legs, back and head) and works for arbitrary human motions. Experiments on the recently released TNT15 dataset show that, using the same number of sensors, SIP achieves higher accuracy than the dataset baseline without using any video data. We further demonstrate the effectiveness of SIP on newly recorded challenging motions in outdoor scenarios such as climbing or jumping over a wall.
Tasks	3D Human Pose Estimation, Motion Capture, Pose Estimation
Published	2017-03-23
URL	http://arxiv.org/abs/1703.08014v2
PDF	http://arxiv.org/pdf/1703.08014v2.pdf
PWC	https://paperswithcode.com/paper/sparse-inertial-poser-automatic-3d-human-pose
Repo
Framework