October 16, 2019

2911 words 14 mins read

Paper Group ANR 1153

Using machine learning to create high-efficiency freeform illumination design tools. Compression of phase-only holograms with JPEG standard and deep learning. Learning Latent Beliefs and Performing Epistemic Reasoning for Efficient and Meaningful Dialog Management. Machine Learning of Space-Fractional Differential Equations. Deep Generative Modelin …

Using machine learning to create high-efficiency freeform illumination design tools


Title	Using machine learning to create high-efficiency freeform illumination design tools
Authors	Caleb Gannon, Rongguang Liang
Abstract	We present a method for improving the efficiency and user experience of freeform illumination design with machine learning. By utilizing orthogonal polynomials to interface with artificial neural networks, we are able to generalize relationships between freeform surface shapes and design parameters. Then, by training the network to generalize the relationship between high-level design goals and final performance, we were able to transform what is traditionally a difficult and computationally intensive problem into a compact, user friendly form. The potential of the proposed method is demonstrated through the design of uniform square patterns from off-axis positions and rectangular patterns of tuneable aspect ratios and distances from the target.
Tasks
Published	2018-12-12
URL	http://arxiv.org/abs/1903.11166v1
PDF	http://arxiv.org/pdf/1903.11166v1.pdf
PWC	https://paperswithcode.com/paper/using-machine-learning-to-create-high
Repo
Framework

Compression of phase-only holograms with JPEG standard and deep learning


Title	Compression of phase-only holograms with JPEG standard and deep learning
Authors	Shuming Jiao, Zhi Jin, Chenliang Chang, Changyuan Zhou, Wenbin Zou, Xia Li
Abstract	It is a critical issue to reduce the enormous amount of data in the processing, storage and transmission of a hologram in digital format. In photograph compression, the JPEG standard is commonly supported by almost every system and device. It will be favorable if JPEG standard is applicable to hologram compression, with advantages of universal compatibility. However, the reconstructed image from a JPEG compressed hologram suffers from severe quality degradation since some high frequency features in the hologram will be lost during the compression process. In this work, we employ a deep convolutional neural network to reduce the artifacts in a JPEG compressed hologram. Simulation and experimental results reveal that our proposed “JPEG + deep learning” hologram compression scheme can achieve satisfactory reconstruction results for a computer-generated phase-only hologram after compression.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03811v1
PDF	http://arxiv.org/pdf/1806.03811v1.pdf
PWC	https://paperswithcode.com/paper/compression-of-phase-only-holograms-with-jpeg
Repo
Framework

Learning Latent Beliefs and Performing Epistemic Reasoning for Efficient and Meaningful Dialog Management


Title	Learning Latent Beliefs and Performing Epistemic Reasoning for Efficient and Meaningful Dialog Management
Authors	Aishwarya Chhabra, Pratik Saini, Amit Sangroya, C. Anantaram
Abstract	Many dialogue management frameworks allow the system designer to directly define belief rules to implement an efficient dialog policy. Because these rules are directly defined, the components are said to be hand-crafted. As dialogues become more complex, the number of states, transitions, and policy decisions becomes very large. To facilitate the dialog policy design process, we propose an approach to automatically learn belief rules using a supervised machine learning approach. We validate our ideas in Student-Advisor conversation domain, where we extract latent beliefs like student is curious, confused and neutral, etc. Further, we also perform epistemic reasoning that helps to tailor the dialog according to student’s emotional state and hence improve the overall effectiveness of the dialog system. Our latent belief identification approach shows an accuracy of 87% and this results in efficient and meaningful dialog management.
Tasks	Dialogue Management
Published	2018-11-26
URL	https://arxiv.org/abs/1811.10238v2
PDF	https://arxiv.org/pdf/1811.10238v2.pdf
PWC	https://paperswithcode.com/paper/learning-latent-beliefs-and-performing
Repo
Framework

Machine Learning of Space-Fractional Differential Equations


Title	Machine Learning of Space-Fractional Differential Equations
Authors	Mamikon Gulian, Maziar Raissi, Paris Perdikaris, George Karniadakis
Abstract	Data-driven discovery of “hidden physics” – i.e., machine learning of differential equation models underlying observed data – has recently been approached by embedding the discovery problem into a Gaussian Process regression of spatial data, treating and discovering unknown equation parameters as hyperparameters of a modified “physics informed” Gaussian Process kernel. This kernel includes the parametrized differential operators applied to a prior covariance kernel. We extend this framework to linear space-fractional differential equations. The methodology is compatible with a wide variety of fractional operators in $\mathbb{R}^d$ and stationary covariance kernels, including the Matern class, and can optimize the Matern parameter during training. We provide a user-friendly and feasible way to perform fractional derivatives of kernels, via a unified set of d-dimensional Fourier integral formulas amenable to generalized Gauss-Laguerre quadrature. The implementation of fractional derivatives has several benefits. First, it allows for discovering fractional-order PDEs for systems characterized by heavy tails or anomalous diffusion, bypassing the analytical difficulty of fractional calculus. Data sets exhibiting such features are of increasing prevalence in physical and financial domains. Second, a single fractional-order archetype allows for a derivative of arbitrary order to be learned, with the order itself being a parameter in the regression. This is advantageous even when used for discovering integer-order equations; the user is not required to assume a “dictionary” of derivatives of various orders, and directly controls the parsimony of the models being discovered. We illustrate on several examples, including fractional-order interpolation of advection-diffusion and modeling relative stock performance in the S&P 500 with alpha-stable motion via a fractional diffusion equation.
Tasks
Published	2018-08-02
URL	https://arxiv.org/abs/1808.00931v3
PDF	https://arxiv.org/pdf/1808.00931v3.pdf
PWC	https://paperswithcode.com/paper/machine-learning-of-space-fractional
Repo
Framework

Deep Generative Modeling for Scene Synthesis via Hybrid Representations


Title	Deep Generative Modeling for Scene Synthesis via Hybrid Representations
Authors	Zaiwei Zhang, Zhenpei Yang, Chongyang Ma, Linjie Luo, Alexander Huth, Etienne Vouga, Qixing Huang
Abstract	We present a deep generative scene modeling technique for indoor environments. Our goal is to train a generative model using a feed-forward neural network that maps a prior distribution (e.g., a normal distribution) to the distribution of primary objects in indoor scenes. We introduce a 3D object arrangement representation that models the locations and orientations of objects, based on their size and shape attributes. Moreover, our scene representation is applicable for 3D objects with different multiplicities (repetition counts), selected from a database. We show a principled way to train this model by combining discriminator losses for both a 3D object arrangement representation and a 2D image-based representation. We demonstrate the effectiveness of our scene representation and the deep learning method on benchmark datasets. We also show the applications of this generative model in scene interpolation and scene completion.
Tasks
Published	2018-08-06
URL	http://arxiv.org/abs/1808.02084v1
PDF	http://arxiv.org/pdf/1808.02084v1.pdf
PWC	https://paperswithcode.com/paper/deep-generative-modeling-for-scene-synthesis
Repo
Framework

Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility


Title	Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility
Authors	Joseph Y. Halpern, Max Kleiman-Weiner
Abstract	We provide formal definitions of degree of blameworthiness and intention relative to an epistemic state (a probability over causal models and a utility function on outcomes). These, together with a definition of actual causality, provide the key ingredients for moral responsibility judgments. We show that these definitions give insight into commonsense intuitions in a variety of puzzling cases from the literature.
Tasks
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05903v1
PDF	http://arxiv.org/pdf/1810.05903v1.pdf
PWC	https://paperswithcode.com/paper/towards-formal-definitions-of-blameworthiness
Repo
Framework

A Train Status Assistant for Indian Railways


Title	A Train Status Assistant for Indian Railways
Authors	Himadri Mishra, Ramashish Gaurav, Biplav Srivastava
Abstract	Trains are part-and-parcel of every day lives in countries with large, diverse, multi-lingual population like India. Consequently, an assistant which can accurately predict and explain train delays will help people and businesses alike. We present a novel conversation agent which can engage with people about train status and inform them about its delay at in-line stations. It is trained on past delay data from a subset of trains and generalizes to others.
Tasks
Published	2018-09-23
URL	http://arxiv.org/abs/1809.08509v1
PDF	http://arxiv.org/pdf/1809.08509v1.pdf
PWC	https://paperswithcode.com/paper/a-train-status-assistant-for-indian-railways
Repo
Framework

A Primer on Causality in Data Science


Title	A Primer on Causality in Data Science
Authors	Hachem Saddiki, Laura B. Balzer
Abstract	Many questions in Data Science are fundamentally causal in that our objective is to learn the effect of some exposure, randomized or not, on an outcome interest. Even studies that are seemingly non-causal, such as those with the goal of prediction or prevalence estimation, have causal elements, including differential censoring or measurement. As a result, we, as Data Scientists, need to consider the underlying causal mechanisms that gave rise to the data, rather than simply the pattern or association observed in those data. In this work, we review the ‘Causal Roadmap’ of Petersen and van der Laan (2014) to provide an introduction to some key concepts in causal inference. Similar to other causal frameworks, the steps of the Roadmap include clearly stating the scientific question, defining of the causal model, translating the scientific question into a causal parameter, assessing the assumptions needed to express the causal parameter as a statistical estimand, implementation of statistical estimators including parametric and semi-parametric methods, and interpretation of our findings. We believe that using such a framework in Data Science will help to ensure that our statistical analyses are guided by the scientific question driving our research, while avoiding over-interpreting our results. We focus on the effect of an exposure occurring at a single time point and highlight the use of targeted maximum likelihood estimation (TMLE) with Super Learner.
Tasks	Causal Inference
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02408v2
PDF	http://arxiv.org/pdf/1809.02408v2.pdf
PWC	https://paperswithcode.com/paper/a-primer-on-causality-in-data-science
Repo
Framework

Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation


Title	Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
Authors	Siyuan Huang, Siyuan Qi, Yinxue Xiao, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu
Abstract	Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are ineffective or only tackle the problem partially. In this paper, we propose an end-to-end model that simultaneously solves all three tasks in real-time given only a single RGB image. The essence of the proposed method is to improve the prediction by i) parametrizing the targets (e.g., 3D boxes) instead of directly estimating the targets, and ii) cooperative training across different modules in contrast to training these modules individually. Specifically, we parametrize the 3D object bounding boxes by the predictions from several modules, i.e., 3D camera pose and object attributes. The proposed method provides two major advantages: i) The parametrization helps maintain the consistency between the 2D image and the 3D world, thus largely reducing the prediction variances in 3D coordinates. ii) Constraints can be imposed on the parametrization to train different modules simultaneously. We call these constraints “cooperative losses” as they enable the joint training and inference. We employ three cooperative losses for 3D bounding boxes, 2D projections, and physical constraints to estimate a geometrically consistent and physically plausible 3D scene. Experiments on the SUN RGB-D dataset shows that the proposed method significantly outperforms prior approaches on 3D object detection, 3D layout estimation, 3D camera pose estimation, and holistic scene understanding.
Tasks	3D Object Detection, Object Detection, Pose Estimation, Scene Understanding
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13049v2
PDF	http://arxiv.org/pdf/1810.13049v2.pdf
PWC	https://paperswithcode.com/paper/cooperative-holistic-scene-understanding
Repo
Framework

Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation


Title	Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation
Authors	Jungwook Lee, Sean Walsh, Ali Harakeh, Steven L. Waslander
Abstract	Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations. Reducing both task complexity and the amount of task switching done by annotators is key to reducing the effort and time required to generate 3D bounding box annotations. This paper introduces a novel ground truth generation method that combines human supervision with pretrained neural networks to generate per-instance 3D point cloud segmentation, 3D bounding boxes, and class annotations. The annotators provide object anchor clicks which behave as a seed to generate instance segmentation results in 3D. The points belonging to each instance are then used to regress object centroids, bounding box dimensions, and object orientation. Our proposed annotation scheme requires 30x lower human annotation time. We use the KITTI 3D object detection dataset to evaluate the efficiency and the quality of our annotation scheme. We also test the the proposed scheme on previously unseen data from the Autonomoose self-driving vehicle to demonstrate generalization capabilities of the network.
Tasks	3D Object Detection, Autonomous Driving, Instance Segmentation, Object Detection, Semantic Segmentation
Published	2018-07-16
URL	http://arxiv.org/abs/1807.06072v1
PDF	http://arxiv.org/pdf/1807.06072v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-pre-trained-3d-object-detection
Repo
Framework

On deep speaker embeddings for text-independent speaker recognition


Title	On deep speaker embeddings for text-independent speaker recognition
Authors	Sergey Novoselov, Andrey Shulipa, Ivan Kremnev, Alexandr Kozlov, Vadim Shchemelinin
Abstract	We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedding extractor. Cosine similarity is an effective metric for speaker verification in this embedding space. We also address the problem of choosing an architecture for the extractor. We found that deep networks with residual frame level connections outperform wide but relatively shallow architectures. This paper also proposes several improvements for previous DNN-based extractor systems to increase the speaker recognition accuracy. We show that the discriminatively trained similarity metric learning approach outperforms the standard LDA-PLDA method as an embedding backend. The results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate robustness of the proposed systems when dealing with close to real-life conditions.
Tasks	Metric Learning, Speaker Recognition, Speaker Verification, Text-Independent Speaker Recognition
Published	2018-04-26
URL	http://arxiv.org/abs/1804.10080v1
PDF	http://arxiv.org/pdf/1804.10080v1.pdf
PWC	https://paperswithcode.com/paper/on-deep-speaker-embeddings-for-text
Repo
Framework

Intrinsic Gaussian processes on complex constrained domains


Title	Intrinsic Gaussian processes on complex constrained domains
Authors	Mu Niu, Pokman Cheung, Lizhen Lin, Zhenwen Dai, Neil Lawrence, David Dunson
Abstract	We propose a class of intrinsic Gaussian processes (in-GPs) for interpolation, regression and classification on manifolds with a primary focus on complex constrained domains or irregular shaped spaces arising as subsets or submanifolds of R, R2, R3 and beyond. For example, in-GPs can accommodate spatial domains arising as complex subsets of Euclidean space. in-GPs respect the potentially complex boundary or interior conditions as well as the intrinsic geometry of the spaces. The key novelty of the proposed approach is to utilise the relationship between heat kernels and the transition density of Brownian motion on manifolds for constructing and approximating valid and computationally feasible covariance kernels. This enables in-GPs to be practically applied in great generality, while existing approaches for smoothing on constrained domains are limited to simple special cases. The broad utilities of the in-GP approach is illustrated through simulation studies and data examples.
Tasks	Gaussian Processes
Published	2018-01-03
URL	http://arxiv.org/abs/1801.01061v1
PDF	http://arxiv.org/pdf/1801.01061v1.pdf
PWC	https://paperswithcode.com/paper/intrinsic-gaussian-processes-on-complex
Repo
Framework

A Novel Low-cost FPGA-based Real-time Object Tracking System


Title	A Novel Low-cost FPGA-based Real-time Object Tracking System
Authors	Peng Gao, Ruyue Yuan, Zhicong Lin, Linsheng Zhang, Yan Zhang
Abstract	In current visual object tracking system, the CPU or GPU-based visual object tracking systems have high computational cost and consume a prohibitive amount of power. Therefore, in this paper, to reduce the computational burden of the Camshift algorithm, we propose a novel visual object tracking algorithm by exploiting the properties of the binary classifier and Kalman predictor. Moreover, we present a low-cost FPGA-based real-time object tracking hardware architecture. Extensive evaluations on OTB benchmark demonstrate that the proposed system has extremely compelling real-time, stability and robustness. The evaluation results show that the accuracy of our algorithm is about 48%, and the average speed is about 309 frames per second.
Tasks	Object Tracking, Visual Object Tracking
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05535v2
PDF	http://arxiv.org/pdf/1804.05535v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-low-cost-fpga-based-real-time-object
Repo
Framework

Instance-Level Explanations for Fraud Detection: A Case Study


Title	Instance-Level Explanations for Fraud Detection: A Case Study
Authors	Dennis Collaris, Leo M. Vink, Jarke J. van Wijk
Abstract	Fraud detection is a difficult problem that can benefit from predictive modeling. However, the verification of a prediction is challenging; for a single insurance policy, the model only provides a prediction score. We present a case study where we reflect on different instance-level model explanation techniques to aid a fraud detection team in their work. To this end, we designed two novel dashboards combining various state-of-the-art explanation techniques. These enable the domain expert to analyze and understand predictions, dramatically speeding up the process of filtering potential fraud cases. Finally, we discuss the lessons learned and outline open research issues.
Tasks	Fraud Detection
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07129v1
PDF	http://arxiv.org/pdf/1806.07129v1.pdf
PWC	https://paperswithcode.com/paper/instance-level-explanations-for-fraud
Repo
Framework

Neural Image Decompression: Learning to Render Better Image Previews


Title	Neural Image Decompression: Learning to Render Better Image Previews
Authors	Shumeet Baluja, Dave Marwood, Nick Johnston, Michele Covell
Abstract	A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints. To satisfy these requests, it has become standard practice for websites to transmit small and extremely compressed image previews as part of the initial page-load process. Recent work, based on an adaptive triangulation of the target image, has shown the ability to generate thumbnails of full images at extreme compression rates: 200 bytes or less with impressive gains (in terms of PSNR and SSIM) over both JPEG and WebP standards. However, qualitative assessments and preservation of semantic content can be less favorable. We present a novel method to significantly improve the reconstruction quality of the original image with no changes to the encoded information. Our neural-based decoding not only achieves higher PSNR and SSIM scores than the original methods, but also yields a substantial increase in semantic-level content preservation. In addition, by keeping the same encoding stream, our solution is completely inter-operable with the original decoder. The end result is suitable for a range of small-device deployments, as it involves only a single forward-pass through a small, scalable network.
Tasks
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02831v1
PDF	http://arxiv.org/pdf/1812.02831v1.pdf
PWC	https://paperswithcode.com/paper/neural-image-decompression-learning-to-render
Repo
Framework