October 17, 2019

3005 words 15 mins read

Paper Group ANR 965

Introducing Quantum-Like Influence Diagrams for Violations of the Sure Thing Principle. Domain Randomization for Scene-Specific Car Detection and Pose Estimation. Improving GANs Using Optimal Transport. Deep Imitative Models for Flexible Inference, Planning, and Control. Optimization of computational budget for power system risk assessment. Limitat …

Introducing Quantum-Like Influence Diagrams for Violations of the Sure Thing Principle


Title	Introducing Quantum-Like Influence Diagrams for Violations of the Sure Thing Principle
Authors	Catarina Moreira, Andreas Wichert
Abstract	It is the focus of this work to extend and study the previously proposed quantum-like Bayesian networks to deal with decision-making scenarios by incorporating the notion of maximum expected utility in influence diagrams. The general idea is to take advantage of the quantum interference terms produced in the quantum-like Bayesian Network to influence the probabilities used to compute the expected utility of some action. This way, we are not proposing a new type of expected utility hypothesis. On the contrary, we are keeping it under its classical definition. We are only incorporating it as an extension of a probabilistic graphical model in a compact graphical representation called an influence diagram in which the utility function depends on the probabilistic influences of the quantum-like Bayesian network. Our findings suggest that the proposed quantum-like influence digram can indeed take advantage of the quantum interference effects of quantum-like Bayesian Networks to maximise the utility of a cooperative behaviour in detriment of a fully rational defect behaviour under the prisoner’s dilemma game.
Tasks	Decision Making
Published	2018-07-16
URL	http://arxiv.org/abs/1807.06142v1
PDF	http://arxiv.org/pdf/1807.06142v1.pdf
PWC	https://paperswithcode.com/paper/introducing-quantum-like-influence-diagrams
Repo
Framework

Domain Randomization for Scene-Specific Car Detection and Pose Estimation


Title	Domain Randomization for Scene-Specific Car Detection and Pose Estimation
Authors	Rawal Khirodkar, Donghyun Yoo, Kris M. Kitani
Abstract	We address the issue of domain gap when making use of synthetic data to train a scene-specific object detector and pose estimator. While previous works have shown that the constraints of learning a scene-specific model can be leveraged to create geometrically and photometrically consistent synthetic data, care must be taken to design synthetic content which is as close as possible to the real-world data distribution. In this work, we propose to solve domain gap through the use of appearance randomization to generate a wide range of synthetic objects to span the space of realistic images for training. An ablation study of our results is presented to delineate the individual contribution of different components in the randomization process. We evaluate our method on VIRAT, UA-DETRAC, EPFL-Car datasets, where we demonstrate that using scene specific domain randomized synthetic data is better than fine-tuning off-the-shelf models on limited real data.
Tasks	Pose Estimation
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05939v1
PDF	http://arxiv.org/pdf/1811.05939v1.pdf
PWC	https://paperswithcode.com/paper/domain-randomization-for-scene-specific-car
Repo
Framework

Improving GANs Using Optimal Transport


Title	Improving GANs Using Optimal Transport
Authors	Tim Salimans, Han Zhang, Alec Radford, Dimitris Metaxas
Abstract	We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance defined in an adversarially learned feature space, resulting in a highly discriminative distance function with unbiased mini-batch gradients. Experimentally we show OT-GAN to be highly stable when trained with large mini-batches, and we present state-of-the-art results on several popular benchmark problems for image generation.
Tasks	Image Generation
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05573v1
PDF	http://arxiv.org/pdf/1803.05573v1.pdf
PWC	https://paperswithcode.com/paper/improving-gans-using-optimal-transport
Repo
Framework

Deep Imitative Models for Flexible Inference, Planning, and Control


Title	Deep Imitative Models for Flexible Inference, Planning, and Control
Authors	Nicholas Rhinehart, Rowan McAllister, Sergey Levine
Abstract	Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to achieve goals. Yet, reward functions that evoke desirable behavior are often difficult to specify. In this paper, we propose Imitative Models to combine the benefits of IL and goal-directed planning. Imitative Models are probabilistic predictive models of desirable behavior able to plan interpretable expert-like trajectories to achieve specified goals. We derive families of flexible goal objectives, including constrained goal regions, unconstrained goal sets, and energy-based goals. We show that our method can use these objectives to successfully direct behavior. Our method substantially outperforms six IL approaches and a planning-based approach in a dynamic simulated autonomous driving task, and is efficiently learned from expert demonstrations without online data collection. We also show our approach is robust to poorly specified goals, such as goals on the wrong side of the road.
Tasks	Autonomous Driving, Imitation Learning
Published	2018-10-15
URL	https://arxiv.org/abs/1810.06544v4
PDF	https://arxiv.org/pdf/1810.06544v4.pdf
PWC	https://paperswithcode.com/paper/deep-imitative-models-for-flexible-inference
Repo
Framework

Optimization of computational budget for power system risk assessment


Title	Optimization of computational budget for power system risk assessment
Authors	Benjamin Donnot, Isabelle Guyon, Antoine Marot, Marc Schoenauer, Patrick Panciatici
Abstract	We address the problem of maintaining high voltage power transmission networks in security at all time, namely anticipating exceeding of thermal limit for eventual single line disconnection (whatever its cause may be) by running slow, but accurate, physical grid simulators. New conceptual frameworks are calling for a probabilistic risk-based security criterion. However, these approaches suffer from high requirements in terms of tractability. Here, we propose a new method to assess the risk. This method uses both machine learning techniques (artificial neural networks) and more standard simulators based on physical laws. More specifically we train neural networks to estimate the overall dangerousness of a grid state. A classical benchmark problem (manpower 118 buses test case) is used to show the strengths of the proposed method.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01174v1
PDF	http://arxiv.org/pdf/1805.01174v1.pdf
PWC	https://paperswithcode.com/paper/optimization-of-computational-budget-for
Repo
Framework

Limitations in learning an interpreted language with recurrent models


Title	Limitations in learning an interpreted language with recurrent models
Authors	Denis Paperno
Abstract	In this submission I report work in progress on learning simplified interpreted languages by means of recurrent models. The data is constructed to reflect core properties of natural language as modeled in formal syntax and semantics: recursive syntactic structure and compositionality. Preliminary results suggest that LSTM networks do generalise to compositional interpretation, albeit only in the most favorable learning setting, with a well-paced curriculum, extensive training data, and left-to-right (but not right-to-left) composition.
Tasks
Published	2018-09-11
URL	http://arxiv.org/abs/1809.04128v1
PDF	http://arxiv.org/pdf/1809.04128v1.pdf
PWC	https://paperswithcode.com/paper/limitations-in-learning-an-interpreted
Repo
Framework

Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation


Title	Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation
Authors	Mykhaylo Andriluka, Jasper R. R. Uijlings, Vittorio Ferrari
Abstract	We introduce Fluid Annotation, an intuitive human-machine collaboration interface for annotating the class label and outline of every object and background region in an image. Fluid annotation is based on three principles: (I) Strong Machine-Learning aid. We start from the output of a strong neural network model, which the annotator can edit by correcting the labels of existing regions, adding new regions to cover missing objects, and removing incorrect regions. The edit operations are also assisted by the model. (II) Full image annotation in a single pass. As opposed to performing a series of small annotation tasks in isolation, we propose a unified interface for full image annotation in a single pass. (III) Empower the annotator. We empower the annotator to choose what to annotate and in which order. This enables concentrating on what the machine does not already know, i.e. putting human effort only on the errors it made. This helps using the annotation budget effectively. Through extensive experiments on the COCO+Stuff dataset, we demonstrate that Fluid Annotation leads to accurate annotations very efficiently, taking three times less annotation time than the popular LabelMe interface.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07527v5
PDF	http://arxiv.org/pdf/1806.07527v5.pdf
PWC	https://paperswithcode.com/paper/fluid-annotation-a-human-machine
Repo
Framework

Considering Race a Problem of Transfer Learning


Title	Considering Race a Problem of Transfer Learning
Authors	Akbir Khan, Marwa Mahmoud
Abstract	As biometric applications are fielded to serve large population groups, issues of performance differences between individual sub-groups are becoming increasingly important. In this paper we examine cases where we believe race is one such factor. We look in particular at two forms of problem; facial classification and image synthesis. We take the novel approach of considering race as a boundary for transfer learning in both the task (facial classification) and the domain (synthesis over distinct datasets). We demonstrate a series of techniques to improve transfer learning of facial classification; outperforming similar models trained in the target’s own domain. We conduct a study to evaluate the performance drop of Generative Adversarial Networks trained to conduct image synthesis, in this process, we produce a new annotation for the Celeb-A dataset by race. These networks are trained solely on one race and tested on another - demonstrating the subsets of the CelebA to be distinct domains for this task.
Tasks	Image Generation, Transfer Learning
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04751v1
PDF	http://arxiv.org/pdf/1812.04751v1.pdf
PWC	https://paperswithcode.com/paper/considering-race-a-problem-of-transfer
Repo
Framework

What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems


Title	What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems
Authors	Owen Lahav, Nicholas Mastronarde, Mihaela van der Schaar
Abstract	Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees, are inherently human-interpretable, which has not been empirically tested. Additionally, past efforts have focused exclusively on comprehension, neglecting to explore the trust component necessary to convince non-technical experts, such as clinicians, to utilize ML models in practice. In this paper, we posit that reinforcement learning (RL) can be used to learn what is interpretable to different users and, consequently, build their trust in ML models. To validate this idea, we first train a neural network to provide risk assessments for heart failure patients. We then design a RL-based clinical decision-support system (DSS) around the neural network model, which can learn from its interactions with users. We conduct an experiment involving a diverse set of clinicians from multiple institutions in three different countries. Our results demonstrate that ML experts cannot accurately predict which system outputs will maximize clinicians’ confidence in the underlying neural network model, and suggest additional findings that have broad implications to the future of research into ML interpretability and the use of ML in medicine.
Tasks
Published	2018-11-27
URL	https://arxiv.org/abs/1811.10799v2
PDF	https://arxiv.org/pdf/1811.10799v2.pdf
PWC	https://paperswithcode.com/paper/what-is-interpretable-using-machine-learning
Repo
Framework

Real time expert system for anomaly detection of aerators based on computer vision technology and existing surveillance cameras


Title	Real time expert system for anomaly detection of aerators based on computer vision technology and existing surveillance cameras
Authors	Yeqi Liu, Yingyi Chen, Huihui Yu, Xiaomin Fang, Chuanyang Gong
Abstract	Aerators are essential and crucial auxiliary devices in intensive culture, especially in industrial culture in China. The traditional methods cannot accurately detect abnormal condition of aerators in time. Surveillance cameras are widely used as visual perception modules of the Internet of Things, and then using these widely existing surveillance cameras to realize real-time anomaly detection of aerators is a cost-free and easy-to-promote method. However, it is difficult to develop such an expert system due to some technical and applied challenges, e.g., illumination, occlusion, complex background, etc. To tackle these aforementioned challenges, we propose a real-time expert system based on computer vision technology and existing surveillance cameras for anomaly detection of aerators, which consists of two modules, i.e., object region detection and working state detection. First, it is difficult to detect the working state for some small object regions in whole images, and the time complexity of global feature comparison is also high, so we present an object region detection method based on the region proposal idea. Moreover, we propose a novel algorithm called reference frame Kanade-Lucas-Tomasi (RF-KLT) algorithm for motion feature extraction in fixed regions. Then, we present a dimension reduction method of time series for establishing a feature dataset with obvious boundaries between classes. Finally, we use machine learning algorithms to build the feature classifier. The experimental results in both the actual video dataset and the augmented video dataset show that the accuracy for detecting object region and working state of aerators is 100% and 99.9% respectively, and the detection speed is 77-333 frames per second (FPS) according to the different types of surveillance cameras.
Tasks	Anomaly Detection, Dimensionality Reduction, Time Series
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04108v3
PDF	http://arxiv.org/pdf/1810.04108v3.pdf
PWC	https://paperswithcode.com/paper/real-time-expert-system-for-anomaly-detection
Repo
Framework

Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World


Title	Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World
Authors	Matteo Fabbri, Fabio Lanzi, Simone Calderara, Andrea Palazzi, Roberto Vezzani, Rita Cucchiara
Abstract	Multi-People Tracking in an open-world setting requires a special effort in precise detection. Moreover, temporal continuity in the detection phase gains more importance when scene cluttering introduces the challenging problems of occluded targets. For the purpose, we propose a deep network architecture that jointly extracts people body parts and associates them across short temporal spans. Our model explicitly deals with occluded body parts, by hallucinating plausible solutions of not visible joints. We propose a new end-to-end architecture composed by four branches (visible heatmaps, occluded heatmaps, part affinity fields and temporal affinity fields) fed by a time linker feature extractor. To overcome the lack of surveillance data with tracking, body part and occlusion annotations we created the vastest Computer Graphics dataset for people tracking in urban scenarios by exploiting a photorealistic videogame. It is up to now the vastest dataset (about 500.000 frames, almost 10 million body poses) of human body parts for people tracking in urban scenarios. Our architecture trained on virtual data exhibits good generalization capabilities also on public real tracking benchmarks, when image resolution and sharpness are high enough, producing reliable tracklets useful for further batch data association or re-id modules.
Tasks
Published	2018-03-22
URL	http://arxiv.org/abs/1803.08319v3
PDF	http://arxiv.org/pdf/1803.08319v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-detect-and-track-visible-and
Repo
Framework

Clustering and Semi-Supervised Classification for Clickstream Data via Mixture Models


Title	Clustering and Semi-Supervised Classification for Clickstream Data via Mixture Models
Authors	Michael P. B. Gallaugher, Paul D. McNicholas
Abstract	Finite mixture models have been used for unsupervised learning for over 60 years, and their use within the semi-supervised paradigm is becoming more commonplace. Clickstream data is one of the various emerging data types that demands particular attention because there is a notable paucity of statistical learning approaches currently available. A mixture of first order continuous time Markov models is introduced for unsupervised and semi-supervised learning of clickstream data. This approach assumes continuous time, which distinguishes it from existing mixture model-based approaches; practically, this allows account to be taken of the amount of time each user spends on each website. The approach is evaluated, and compared to the discrete time approach, using simulated and real data.
Tasks
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04849v1
PDF	http://arxiv.org/pdf/1802.04849v1.pdf
PWC	https://paperswithcode.com/paper/clustering-and-semi-supervised-classification
Repo
Framework

Talent Search and Recommendation Systems at LinkedIn: Practical Challenges and Lessons Learned


Title	Talent Search and Recommendation Systems at LinkedIn: Practical Challenges and Lessons Learned
Authors	Sahin Cem Geyik, Qi Guo, Bo Hu, Cagri Ozcaglar, Ketan Thakkar, Xianren Wu, Krishnaram Kenthapadi
Abstract	LinkedIn Talent Solutions business contributes to around 65% of LinkedIn’s annual revenue, and provides tools for job providers to reach out to potential candidates and for job seekers to find suitable career opportunities. LinkedIn’s job ecosystem has been designed as a platform to connect job providers and job seekers, and to serve as a marketplace for efficient matching between potential candidates and job openings. A key mechanism to help achieve these goals is the LinkedIn Recruiter product, which enables recruiters to search for relevant candidates and obtain candidate recommendations for their job postings. In this work, we highlight a set of unique information retrieval, system, and modeling challenges associated with talent search and recommendation systems.
Tasks	Information Retrieval, Recommendation Systems
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06481v1
PDF	http://arxiv.org/pdf/1809.06481v1.pdf
PWC	https://paperswithcode.com/paper/talent-search-and-recommendation-systems-at
Repo
Framework

Wireless Network Intelligence at the Edge


Title	Wireless Network Intelligence at the Edge
Authors	Jihong Park, Sumudu Samarakoon, Mehdi Bennis, Mérouane Debbah
Abstract	Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory and computing resources, limiting their adoption for resource constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, etc.), requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data is unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover training and inference is carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented demonstrating the effectiveness of edge ML in unlocking the full potential of 5G and beyond.
Tasks	Face Recognition, Medical Diagnosis
Published	2018-12-07
URL	https://arxiv.org/abs/1812.02858v2
PDF	https://arxiv.org/pdf/1812.02858v2.pdf
PWC	https://paperswithcode.com/paper/wireless-network-intelligence-at-the-edge
Repo
Framework

Comparison of U-net-based Convolutional Neural Networks for Liver Segmentation in CT


Title	Comparison of U-net-based Convolutional Neural Networks for Liver Segmentation in CT
Authors	Hans Meine, Grzegorz Chlebus, Mohsen Ghafoorian, Itaru Endo, Andrea Schenk
Abstract	Various approaches for liver segmentation in CT have been proposed: Besides statistical shape models, which played a major role in this research area, novel approaches on the basis of convolutional neural networks have been introduced recently. Using a set of 219 liver CT datasets with reference segmentations from liver surgery planning, we evaluate the performance of several neural network classifiers based on 2D and 3D U-net architectures. An interesting observation is that slice-wise approaches perform surprisingly well, with mean and median Dice coefficients above 0.97, and may be preferable over 3D approaches given current hardware and software limitations.
Tasks	Liver Segmentation
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04017v1
PDF	http://arxiv.org/pdf/1810.04017v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-u-net-based-convolutional
Repo
Framework