October 18, 2019

2664 words 13 mins read

Paper Group ANR 486

Real-Time Stereo Vision on FPGAs with SceneScan. DSVO: Direct Stereo Visual Odometry. A Low Effort Approach to Structured CNN Design Using PCA. Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series. Realizing Intelligence. Hierarchical Reinforcement Learning with Hindsight. Automated labeling of bugs and tickets using attention …

Real-Time Stereo Vision on FPGAs with SceneScan


Title	Real-Time Stereo Vision on FPGAs with SceneScan
Authors	Konstantin Schauwecker
Abstract	We present a flexible FPGA stereo vision implementation that is capable of processing up to 100 frames per second or image resolutions up to 3.4 megapixels, while consuming only 8 W of power. The implementation uses a variation of the Semi-Global Matching (SGM) algorithm, which provides superior results compared to many simpler approaches. The stereo matching results are improved significantly through a post-processing chain that operates on the computed cost cube and the disparity map. With this implementation we have created two stand-alone hardware systems for stereo vision, called SceneScan and SceneScan Pro. Both systems have been developed to market maturity and are available from Nerian Vision GmbH.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2018-09-21
URL	http://arxiv.org/abs/1809.07977v1
PDF	http://arxiv.org/pdf/1809.07977v1.pdf
PWC	https://paperswithcode.com/paper/real-time-stereo-vision-on-fpgas-with
Repo
Framework

DSVO: Direct Stereo Visual Odometry


Title	DSVO: Direct Stereo Visual Odometry
Authors	Jiawei Mo, Junaed Sattar
Abstract	This paper proposes a novel approach to stereo visual odometry without stereo matching. It is particularly robust in scenes of repetitive high-frequency textures. Referred to as DSVO (Direct Stereo Visual Odometry), it operates directly on pixel intensities, without any explicit feature matching, and is thus efficient and more accurate than the state-of-the-art stereo-matching-based methods. It applies a semi-direct monocular visual odometry running on one camera of the stereo pair, tracking the camera pose and mapping the environment simultaneously; the other camera is used to optimize the scale of monocular visual odometry. We evaluate DSVO in a number of challenging scenes to evaluate its performance and present comparisons with the state-of-the-art stereo visual odometry algorithms.
Tasks	Monocular Visual Odometry, Stereo Matching, Stereo Matching Hand, Visual Odometry
Published	2018-09-19
URL	https://arxiv.org/abs/1810.03963v2
PDF	https://arxiv.org/pdf/1810.03963v2.pdf
PWC	https://paperswithcode.com/paper/dsvo-direct-stereo-visual-odometry
Repo
Framework

A Low Effort Approach to Structured CNN Design Using PCA


Title	A Low Effort Approach to Structured CNN Design Using PCA
Authors	Isha Garg, Priyadarshini Panda, Kaushik Roy
Abstract	Deep learning models hold state of the art performance in many fields, yet their design is still based on heuristics or grid search methods that often result in overparametrized networks. This work proposes a method to analyze a trained network and deduce an optimized, compressed architecture that preserves accuracy while keeping computational costs tractable. Model compression is an active field of research that targets the problem of realizing deep learning models in hardware. However, most pruning methodologies tend to be experimental, requiring large compute and time intensive iterations of retraining the entire network. We introduce structure into model design by proposing a single shot analysis of a trained network that serves as a first order, low effort approach to dimensionality reduction, by using PCA (Principal Component Analysis). The proposed method simultaneously analyzes the activations of each layer and considers the dimensionality of the space described by the filters generating these activations. It optimizes the architecture in terms of number of layers, and number of filters per layer without any iterative retraining procedures, making it a viable, low effort technique to design efficient networks. We demonstrate the proposed methodology on AlexNet and VGG style networks on the CIFAR-10, CIFAR-100 and ImageNet datasets, and successfully achieve an optimized architecture with a reduction of up to 3.8X and 9X in the number of operations and parameters respectively, while trading off less than 1% accuracy. We also apply the method to MobileNet, and achieve 1.7X and 3.9X reduction in the number of operations and parameters respectively, while improving accuracy by almost one percentage point.
Tasks	Dimensionality Reduction, Model Compression
Published	2018-12-15
URL	https://arxiv.org/abs/1812.06224v4
PDF	https://arxiv.org/pdf/1812.06224v4.pdf
PWC	https://paperswithcode.com/paper/a-low-effort-approach-to-structured-cnn
Repo
Framework

Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series


Title	Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series
Authors	Axel Brando, Jose A. Rodríguez-Serrano, Mauricio Ciprian, Roberto Maestre, Jordi Vitrià
Abstract	Deep Learning is a consolidated, state-of-the-art Machine Learning tool to fit a function when provided with large data sets of examples. However, in regression tasks, the straightforward application of Deep Learning models provides a point estimate of the target. In addition, the model does not take into account the uncertainty of a prediction. This represents a great limitation for tasks where communicating an erroneous prediction carries a risk. In this paper we tackle a real-world problem of forecasting impending financial expenses and incomings of customers, while displaying predictable monetary amounts on a mobile app. In this context, we investigate if we would obtain an advantage by applying Deep Learning models with a Heteroscedastic model of the variance of a network’s output. Experimentally, we achieve a higher accuracy than non-trivial baselines. More importantly, we introduce a mechanism to discard low-confidence predictions, which means that they will not be visible to users. This should help enhance the user experience of our product.
Tasks
Published	2018-07-24
URL	http://arxiv.org/abs/1807.09011v1
PDF	http://arxiv.org/pdf/1807.09011v1.pdf
PWC	https://paperswithcode.com/paper/uncertainty-modelling-in-deep-networks
Repo
Framework

Realizing Intelligence


Title	Realizing Intelligence
Authors	Paul Yaworsky
Abstract	Order exists in the world. The intelligence process enables us to realize that order, to some extent. We provide a high level description of intelligence using simple definitions, basic building blocks, a conceptual framework and general hierarchy. This perspective includes multiple levels of abstraction occurring in space and in time. The resulting model offers simple, useful ways to help realize the essence of intelligence.
Tasks
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02765v1
PDF	http://arxiv.org/pdf/1803.02765v1.pdf
PWC	https://paperswithcode.com/paper/realizing-intelligence
Repo
Framework

Hierarchical Reinforcement Learning with Hindsight


Title	Hierarchical Reinforcement Learning with Hindsight
Authors	Andrew Levy, Robert Platt, Kate Saenko
Abstract	Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks.
Tasks	Hierarchical Reinforcement Learning
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08180v2
PDF	http://arxiv.org/pdf/1805.08180v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-reinforcement-learning-with-1
Repo
Framework

Automated labeling of bugs and tickets using attention-based mechanisms in recurrent neural networks


Title	Automated labeling of bugs and tickets using attention-based mechanisms in recurrent neural networks
Authors	Volodymyr Lyubinets, Taras Boiko, Deon Nicholas
Abstract	We explore solutions for automated labeling of content in bug trackers and customer support systems. In order to do that, we classify content in terms of several criteria, such as priority or product area. In the first part of the paper, we provide an overview of existing methods used for text classification. These methods fall into two categories - the ones that rely on neural networks and the ones that don’t. We evaluate results of several solutions of both kinds. In the second part of the paper we present our own recurrent neural network solution based on hierarchical attention paradigm. It consists of several Hierarchical Attention network blocks with varying Gated Recurrent Unit cell sizes and a complementary shallow network that goes alongside. Lastly, we evaluate above-mentioned methods when predicting fields from two datasets - Arch Linux bug tracker and Chromium bug tracker. Our contributions include a comprehensive benchmark between a variety of methods on relevant datasets; a novel solution that outperforms previous generation methods; and two new datasets that are made public for further research.
Tasks	Text Classification
Published	2018-07-08
URL	http://arxiv.org/abs/1807.02892v1
PDF	http://arxiv.org/pdf/1807.02892v1.pdf
PWC	https://paperswithcode.com/paper/automated-labeling-of-bugs-and-tickets-using
Repo
Framework


Title	Early Identification of Pathogenic Social Media Accounts
Authors	Hamidreza Alvari, Elham Shaabani, Paulo Shakarian
Abstract	Pathogenic Social Media (PSM) accounts such as terrorist supporters exploit large communities of supporters for conducting attacks on social media. Early detection of these accounts is crucial as they are high likely to be key users in making a harmful message “viral”. In this paper, we make the first attempt on utilizing causal inference to identify PSMs within a short time frame around their activity. We propose a time-decay causality metric and incorporate it into a causal community detection-based algorithm. The proposed algorithm is applied to groups of accounts sharing similar causality features and is followed by a classification algorithm to classify accounts as PSM or not. Unlike existing techniques that take significant time to collect information such as network, cascade path, or content, our scheme relies solely on action log of users. Results on a real-world dataset from Twitter demonstrate effectiveness and efficiency of our approach. We achieved precision of 0.84 for detecting PSMs only based on their first 10 days of activity; the misclassified accounts were then detected 10 days later.
Tasks	Causal Inference, Community Detection
Published	2018-09-25
URL	http://arxiv.org/abs/1809.09331v2
PDF	http://arxiv.org/pdf/1809.09331v2.pdf
PWC	https://paperswithcode.com/paper/early-identification-of-pathogenic-social
Repo
Framework

A folded model for compositional data analysis


Title	A folded model for compositional data analysis
Authors	Michail Tsagris, Connie Stewart
Abstract	A folded type model is developed for analyzing compositional data. The proposed model involves an extension of the $\alpha$-transformation for compositional data and provides a new and flexible class of distributions for modeling data defined on the simplex sample space. Despite its rather seemingly complex structure, employment of the EM algorithm guarantees efficient parameter estimation. The model is validated through simulation studies and examples which illustrate that the proposed model performs better in terms of capturing the data structure, when compared to the popular logistic normal distribution, and can be advantageous over a similar model without folding.
Tasks
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07330v2
PDF	http://arxiv.org/pdf/1802.07330v2.pdf
PWC	https://paperswithcode.com/paper/a-folded-model-for-compositional-data
Repo
Framework

Assumption-Based Planning


Title	Assumption-Based Planning
Authors	Damien Pellier, Humbert Fiorino
Abstract	The purpose of the paper is to introduce a new approach of planning called Assumption-Based Planning. This approach is a very interesting way to devise a planner based on a multi-agent system in which the production of a global shared plan is obtained by conjecture/refutation cycles. Contrary to classical approaches, our contribution relies on the agents reasoning that leads to the production of a plan from planning domains. To take into account complex environments and the partial agents knowledge, we propose to consider the planning problem as a defeasible reasoning where the agents exchange proposals and counter-proposals and are able to reason about uncertainty. The argumentation dialogue between agents must not be viewed as a negotiation process but as an investigation process in order to build a plan. In this paper, we focus on the mechanisms that allow an agent to produce `reasonable’ proposals according to its knowledge. \|
Tasks
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08431v1
PDF	http://arxiv.org/pdf/1810.08431v1.pdf
PWC	https://paperswithcode.com/paper/assumption-based-planning
Repo
Framework

Estimating Carotid Pulse and Breathing Rate from Near-infrared Video of the Neck


Title	Estimating Carotid Pulse and Breathing Rate from Near-infrared Video of the Neck
Authors	Weixuan Chen, Javier Hernandez, Rosalind W. Picard
Abstract	Objective: Non-contact physiological measurement is a growing research area that allows capturing vital signs such as heart rate (HR) and breathing rate (BR) comfortably and unobtrusively with remote devices. However, most of the approaches work only in bright environments in which subtle photoplethysmographic and ballistocardiographic signals can be easily analyzed and/or require expensive and custom hardware to perform the measurements. Approach: This work introduces a low-cost method to measure subtle motions associated with the carotid pulse and breathing movement from the neck using near-infrared (NIR) video imaging. A skin reflection model of the neck was established to provide a theoretical foundation for the method. In particular, the method relies on template matching for neck detection, Principal Component Analysis for feature extraction, and Hidden Markov Models for data smoothing. Main Results: We compared the estimated HR and BR measures with ones provided by an FDA-cleared device in a 12-participant laboratory study: the estimates achieved a mean absolute error of 0.36 beats per minute and 0.24 breaths per minute under both bright and dark lighting. Significance: This work advances the possibilities of non-contact physiological measurement in real-life conditions in which environmental illumination is limited and in which the face of the person is not readily available or needs to be protected. Due to the increasing availability of NIR imaging devices, the described methods are readily scalable.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09511v1
PDF	http://arxiv.org/pdf/1805.09511v1.pdf
PWC	https://paperswithcode.com/paper/estimating-carotid-pulse-and-breathing-rate
Repo
Framework

Semi-dense Stereo Matching using Dual CNNs


Title	Semi-dense Stereo Matching using Dual CNNs
Authors	Wendong Mao, Mingjie Wang, Jun Zhou, Minglun Gong
Abstract	A robust solution for semi-dense stereo matching is presented. It utilizes two CNN models for computing stereo matching cost and performing confidence-based filtering, respectively. Compared to existing CNNs-based matching cost generation approaches, our method feeds additional global information into the network so that the learned model can better handle challenging cases, such as lighting changes and lack of textures. Through utilizing non-parametric transforms, our method is also more self-reliant than most existing semi-dense stereo approaches, which rely highly on the adjustment of parameters. The experimental results based on Middlebury Stereo dataset demonstrate that the proposed approach outperforms the state-of-the-art semi-dense stereo approaches.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01369v1
PDF	http://arxiv.org/pdf/1810.01369v1.pdf
PWC	https://paperswithcode.com/paper/semi-dense-stereo-matching-using-dual-cnns
Repo
Framework

Unconstrained Submodular Maximization with Constant Adaptive Complexity


Title	Unconstrained Submodular Maximization with Constant Adaptive Complexity
Authors	Lin Chen, Moran Feldman, Amin Karbasi
Abstract	In this paper, we consider the unconstrained submodular maximization problem. We propose the first algorithm for this problem that achieves a tight $(1/2-\varepsilon)$-approximation guarantee using $\tilde{O}(\varepsilon^{-1})$ adaptive rounds and a linear number of function evaluations. No previously known algorithm for this problem achieves an approximation ratio better than $1/3$ using less than $\Omega(n)$ rounds of adaptivity, where $n$ is the size of the ground set. Moreover, our algorithm easily extends to the maximization of a non-negative continuous DR-submodular function subject to a box constraint and achieves a tight $(1/2-\varepsilon)$-approximation guarantee for this problem while keeping the same adaptive and query complexities.
Tasks
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06603v2
PDF	http://arxiv.org/pdf/1811.06603v2.pdf
PWC	https://paperswithcode.com/paper/unconstrained-submodular-maximization-with
Repo
Framework

Hidden Markov Model Estimation-Based Q-learning for Partially Observable Markov Decision Process


Title	Hidden Markov Model Estimation-Based Q-learning for Partially Observable Markov Decision Process
Authors	Hyung-Jin Yoon, Donghwan Lee, Naira Hovakimyan
Abstract	The objective is to study an on-line Hidden Markov model (HMM) estimation-based Q-learning algorithm for partially observable Markov decision process (POMDP) on finite state and action sets. When the full state observation is available, Q-learning finds the optimal action-value function given the current action (Q function). However, Q-learning can perform poorly when the full state observation is not available. In this paper, we formulate the POMDP estimation into a HMM estimation problem and propose a recursive algorithm to estimate both the POMDP parameter and Q function concurrently. Also, we show that the POMDP estimation converges to a set of stationary points for the maximum likelihood estimate, and the Q function estimation converges to a fixed point that satisfies the Bellman optimality equation weighted on the invariant distribution of the state belief determined by the HMM estimation process.
Tasks	Q-Learning
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06401v2
PDF	http://arxiv.org/pdf/1809.06401v2.pdf
PWC	https://paperswithcode.com/paper/hidden-markov-model-estimation-based-q
Repo
Framework

Abstractive Tabular Dataset Summarization via Knowledge Base Semantic Embeddings


Title	Abstractive Tabular Dataset Summarization via Knowledge Base Semantic Embeddings
Authors	Paul Azunre, Craig Corcoran, David Sullivan, Garrett Honke, Rebecca Ruppel, Sandeep Verma, Jonathon Morgan
Abstract	This paper describes an abstractive summarization method for tabular data which employs a knowledge base semantic embedding to generate the summary. Assuming the dataset contains descriptive text in headers, columns and/or some augmenting metadata, the system employs the embedding to recommend a subject/type for each text segment. Recommendations are aggregated into a small collection of super types considered to be descriptive of the dataset by exploiting the hierarchy of types in a pre-specified ontology. Using February 2015 Wikipedia as the knowledge base, and a corresponding DBpedia ontology as types, we present experimental results on open data taken from several sources–OpenML, CKAN and data.world–to illustrate the effectiveness of the approach.
Tasks	Abstractive Text Summarization
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01503v2
PDF	http://arxiv.org/pdf/1804.01503v2.pdf
PWC	https://paperswithcode.com/paper/abstractive-tabular-dataset-summarization-via
Repo
Framework