October 19, 2019

3191 words 15 mins read

Paper Group ANR 316

Deep Metric Learning with Hierarchical Triplet Loss. An information-theoretic on-line update principle for perception-action coupling. Estimating Bayesian Optimal Treatment Regimes for Dichotomous Outcomes using Observational Data. Offline and Online calibration of Mobile Robot and SLAM Device for Navigation. Resilient Non-Submodular Maximization o …

Deep Metric Learning with Hierarchical Triplet Loss


Title	Deep Metric Learning with Hierarchical Triplet Loss
Authors	Weifeng Ge, Weilin Huang, Dengke Dong, Matthew R. Scott
Abstract	We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to cope with the main limitation of random sampling in training a conventional triplet loss, which is a central issue for deep metric learning. Our main contributions are two-fold. (i) we construct a hierarchical class-level tree where neighboring classes are merged recursively. The hierarchical structure naturally captures the intrinsic data distribution over the whole database. (ii) we formulate the problem of triplet collection by introducing a new violate margin, which is computed dynamically based on the designed hierarchical tree. This allows it to automatically select meaningful hard samples with the guide of global context. It encourages the model to learn more discriminative features from visual similar classes, leading to faster convergence and better performance. Our method is evaluated on the tasks of image retrieval and face recognition, where it outperforms the standard triplet loss substantially by 1%-18%. It achieves new state-of-the-art performance on a number of benchmarks, with much fewer learning iterations.
Tasks	Face Recognition, Image Retrieval, Metric Learning
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06951v1
PDF	http://arxiv.org/pdf/1810.06951v1.pdf
PWC	https://paperswithcode.com/paper/deep-metric-learning-with-hierarchical
Repo
Framework

An information-theoretic on-line update principle for perception-action coupling


Title	An information-theoretic on-line update principle for perception-action coupling
Authors	Zhen Peng, Tim Genewein, Felix Leibfried, Daniel A. Braun
Abstract	Inspired by findings of sensorimotor coupling in humans and animals, there has recently been a growing interest in the interaction between action and perception in robotic systems [Bogh et al., 2016]. Here we consider perception and action as two serial information channels with limited information-processing capacity. We follow [Genewein et al., 2015] and formulate a constrained optimization problem that maximizes utility under limited information-processing capacity in the two channels. As a solution we obtain an optimal perceptual channel and an optimal action channel that are coupled such that perceptual information is optimized with respect to downstream processing in the action module. The main novelty of this study is that we propose an online optimization procedure to find bounded-optimal perception and action channels in parameterized serial perception-action systems. In particular, we implement the perceptual channel as a multi-layer neural network and the action channel as a multinomial distribution. We illustrate our method in a NAO robot simulator with a simplified cup lifting task.
Tasks
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05906v1
PDF	http://arxiv.org/pdf/1804.05906v1.pdf
PWC	https://paperswithcode.com/paper/an-information-theoretic-on-line-update
Repo
Framework

Estimating Bayesian Optimal Treatment Regimes for Dichotomous Outcomes using Observational Data


Title	Estimating Bayesian Optimal Treatment Regimes for Dichotomous Outcomes using Observational Data
Authors	Thomas Klausch, Peter van de Ven, Tim van de Brug, Mark A. van de Wiel, Johannes Berkhof
Abstract	Optimal treatment regimes (OTR) are individualised treatment assignment strategies that identify a medical treatment as optimal given all background information available on the individual. We discuss Bayes optimal treatment regimes estimated using a loss function defined on the bivariate distribution of dichotomous potential outcomes. The proposed approach allows considering more general objectives for the OTR than maximization of an expected outcome (e.g., survival probability) by taking into account, for example, unnecessary treatment burden. As a motivating example we consider the case of oropharynx cancer treatment where unnecessary burden due to chemotherapy is to be avoided while maximizing survival chances. Assuming ignorable treatment assignment we describe Bayesian inference about the OTR including a sensitivity analysis on the unobserved partial association of the potential outcomes. We evaluate the methodology by simulations that apply Bayesian parametric and more flexible non-parametric outcome models. The proposed OTR for oropharynx cancer reduces the frequency of the more burdensome chemotherapy assignment by approximately 75% without reducing the average survival probability. This regime thus offers a strong increase in expected quality of life of patients.
Tasks	Bayesian Inference
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06679v2
PDF	http://arxiv.org/pdf/1809.06679v2.pdf
PWC	https://paperswithcode.com/paper/estimating-bayesian-optimal-treatment-regimes
Repo
Framework


Title	Offline and Online calibration of Mobile Robot and SLAM Device for Navigation
Authors	Ryoichi Ishikawa, Takeshi Oishi, Katsushi Ikeuchi
Abstract	Robot navigation technology is required to accomplish difficult tasks in various environments. In navigation, it is necessary to know the information of the external environments and the state of the robot under the environment. On the other hand, various studies have been done on SLAM technology, which is also used for navigation, but also applied to devices for Mixed Reality and the like. In this paper, we propose a robot-device calibration method for navigation with a device using SLAM technology on a robot. The calibration is performed by using the position and orientation information given by the robot and the device. In the calibration, the most efficient way of movement is clarified according to the restriction of the robot movement. Furthermore, we also show a method to dynamically correct the position and orientation of the robot so that the information of the external environment and the shape information of the robot maintain consistency in order to reduce the dynamic error occurring during navigation. Our method can be easily used for various kinds of robots and localization with sufficient precision for navigation is possible with offline calibration and online position correction. In the experiments, we confirm the parameters obtained by two types of offline calibration according to the degree of freedom of robot movement and validate the effectiveness of online correction method by plotting localized position error during robot’s intense movement. Finally, we show the demonstration of navigation using SLAM device.
Tasks	Calibration, Robot Navigation
Published	2018-04-13
URL	http://arxiv.org/abs/1804.04817v1
PDF	http://arxiv.org/pdf/1804.04817v1.pdf
PWC	https://paperswithcode.com/paper/offline-and-online-calibration-of-mobile
Repo
Framework

Resilient Non-Submodular Maximization over Matroid Constraints


Title	Resilient Non-Submodular Maximization over Matroid Constraints
Authors	Vasileios Tzoumas, Ali Jadbabaie, George J. Pappas
Abstract	The control and sensing of large-scale systems results in combinatorial problems not only for sensor and actuator placement but also for scheduling or observability/controllability. Such combinatorial constraints in system design and implementation can be captured using a structure known as matroids. In particular, the algebraic structure of matroids can be exploited to develop scalable algorithms for sensor and actuator selection, along with quantifiable approximation bounds. However, in large-scale systems, sensors and actuators may fail or may be (cyber-)attacked. The objective of this paper is to focus on resilient matroid-constrained problems arising in control and sensing but in the presence of sensor and actuator failures. In general, resilient matroid-constrained problems are computationally hard. Contrary to the non-resilient case (with no failures), even though they often involve objective functions that are monotone or submodular, no scalable approximation algorithms are known for their solution. In this paper, we provide the first algorithm, that also has the following properties: First, it achieves system-wide resiliency, i.e., the algorithm is valid for any number of denial-of-service attacks or failures. Second, it is scalable, as our algorithm terminates with the same running time as state-of-the-art algorithms for (non-resilient) matroid-constrained optimization. Third, it provides provable approximation bounds on the system performance, since for monotone objective functions our algorithm guarantees a solution close to the optimal. We quantify our algorithm’s approximation performance using a notion of curvature for monotone (not necessarily submodular) set functions. Finally, we support our theoretical analyses with numerical experiments, by considering a control-aware sensor selection scenario, namely, sensing-constrained robot navigation.
Tasks	Robot Navigation
Published	2018-04-02
URL	http://arxiv.org/abs/1804.01013v4
PDF	http://arxiv.org/pdf/1804.01013v4.pdf
PWC	https://paperswithcode.com/paper/resilient-non-submodular-maximization-over
Repo
Framework

A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification


Title	A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification
Authors	Ruizhe Li, Chenghua Lin, Matthew Collinson, Xiao Li, Guanyi Chen
Abstract	Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a DA and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between DAs and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both DAs and topics, as well as information about the interactions between them. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification, yielding better or comparable performance to the state-of-the-art method on three public datasets.
Tasks	Dialogue Act Classification, Dialogue Generation, Intent Detection
Published	2018-10-22
URL	https://arxiv.org/abs/1810.09154v3
PDF	https://arxiv.org/pdf/1810.09154v3.pdf
PWC	https://paperswithcode.com/paper/a-dual-attention-hierarchical-recurrent
Repo
Framework

I Know How You Feel: Emotion Recognition with Facial Landmarks


Title	I Know How You Feel: Emotion Recognition with Facial Landmarks
Authors	Ivona Tautkute, Tomasz Trzcinski, Adam Bielski
Abstract	Classification of human emotions remains an important and challenging task for many computer vision algorithms, especially in the era of humanoid robots which coexist with humans in their everyday life. Currently proposed methods for emotion recognition solve this task using multi-layered convolutional networks that do not explicitly infer any facial features in the classification phase. In this work, we postulate a fundamentally different approach to solve emotion recognition task that relies on incorporating facial landmarks as a part of the classification loss function. To that end, we extend a recently proposed Deep Alignment Network (DAN), that achieves state-of-the-art results in the recent facial landmark recognition challenge, with a term related to facial features. Thanks to this simple modification, our model called EmotionalDAN is able to outperform state-of-the-art emotion classification methods on two challenging benchmark dataset by up to 5%.
Tasks	Emotion Classification, Emotion Recognition
Published	2018-04-22
URL	http://arxiv.org/abs/1805.00326v2
PDF	http://arxiv.org/pdf/1805.00326v2.pdf
PWC	https://paperswithcode.com/paper/i-know-how-you-feel-emotion-recognition-with
Repo
Framework

TextRay: Mining Clinical Reports to Gain a Broad Understanding of Chest X-rays


Title	TextRay: Mining Clinical Reports to Gain a Broad Understanding of Chest X-rays
Authors	Jonathan Laserson, Christine Dan Lantsman, Michal Cohen-Sfady, Itamar Tamir, Eli Goz, Chen Brestel, Shir Bar, Maya Atar, Eldad Elnekave
Abstract	The chest X-ray (CXR) is by far the most commonly performed radiological examination for screening and diagnosis of many cardiac and pulmonary diseases. There is an immense world-wide shortage of physicians capable of providing rapid and accurate interpretation of this study. A radiologist-driven analysis of over two million CXR reports generated an ontology including the 40 most prevalent pathologies on CXR. By manually tagging a relatively small set of sentences, we were able to construct a training set of 959k studies. A deep learning model was trained to predict the findings given the patient frontal and lateral scans. For 12 of the findings we compare the model performance against a team of radiologists and show that in most cases the radiologists agree on average more with the algorithm than with each other.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02121v1
PDF	http://arxiv.org/pdf/1806.02121v1.pdf
PWC	https://paperswithcode.com/paper/textray-mining-clinical-reports-to-gain-a
Repo
Framework

Reinforcement Learning based Recommender System using Biclustering Technique


Title	Reinforcement Learning based Recommender System using Biclustering Technique
Authors	Sungwoon Choi, Heonseok Ha, Uiwon Hwang, Chanju Kim, Jung-Woo Ha, Sungroh Yoon
Abstract	A recommender system aims to recommend items that a user is interested in among many items. The need for the recommender system has been expanded by the information explosion. Various approaches have been suggested for providing meaningful recommendations to users. One of the proposed approaches is to consider a recommender system as a Markov decision process (MDP) problem and try to solve it using reinforcement learning (RL). However, existing RL-based methods have an obvious drawback. To solve an MDP in a recommender system, they encountered a problem with the large number of discrete actions that bring RL to a larger class of problems. In this paper, we propose a novel RL-based recommender system. We formulate a recommender system as a gridworld game by using a biclustering technique that can reduce the state and action space significantly. Using biclustering not only reduces space but also improves the recommendation quality effectively handling the cold-start problem. In addition, our approach can provide users with some explanation why the system recommends certain items. Lastly, we examine the proposed algorithm on a real-world dataset and achieve a better performance than the widely used recommendation algorithm.
Tasks	Recommendation Systems
Published	2018-01-17
URL	http://arxiv.org/abs/1801.05532v1
PDF	http://arxiv.org/pdf/1801.05532v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-based-recommender
Repo
Framework

Resilient Monotone Sequential Maximization


Title	Resilient Monotone Sequential Maximization
Authors	Vasileios Tzoumas, Ali Jadbabaie, George J. Pappas
Abstract	Applications in machine learning, optimization, and control require the sequential selection of a few system elements, such as sensors, data, or actuators, to optimize the system performance across multiple time steps. However, in failure-prone and adversarial environments, sensors get attacked, data get deleted, and actuators fail. Thence, traditional sequential design paradigms become insufficient and, in contrast, resilient sequential designs that adapt against system-wide attacks, deletions, or failures become important. In general, resilient sequential design problems are computationally hard. Also, even though they often involve objective functions that are monotone and (possibly) submodular, no scalable approximation algorithms are known for their solution. In this paper, we provide the first scalable algorithm, that achieves the following characteristics: system-wide resiliency, i.e., the algorithm is valid for any number of denial-of-service attacks, deletions, or failures; adaptiveness, i.e., at each time step, the algorithm selects system elements based on the history of inflicted attacks, deletions, or failures; and provable approximation performance, i.e., the algorithm guarantees for monotone objective functions a solution close to the optimal. We quantify the algorithm’s approximation performance using a notion of curvature for monotone (not necessarily submodular) set functions. Finally, we support our theoretical analyses with simulated experiments, by considering a control-aware sensor scheduling scenario, namely, sensing-constrained robot navigation.
Tasks	Robot Navigation
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07954v3
PDF	http://arxiv.org/pdf/1803.07954v3.pdf
PWC	https://paperswithcode.com/paper/resilient-monotone-sequential-maximization
Repo
Framework

Methodology to analyze the accuracy of 3D objects reconstructed with collaborative robot based monocular LSD-SLAM


Title	Methodology to analyze the accuracy of 3D objects reconstructed with collaborative robot based monocular LSD-SLAM
Authors	Sergey Triputen, Atmaraaj Gopal, Thomas Weber, Christian Hofert, Kristiaan Schreve, Matthias Ratsch
Abstract	SLAM systems are mainly applied for robot navigation while research on feasibility for motion planning with SLAM for tasks like bin-picking, is scarce. Accurate 3D reconstruction of objects and environments is important for planning motion and computing optimal gripper pose to grasp objects. In this work, we propose the methods to analyze the accuracy of a 3D environment reconstructed using a LSD-SLAM system with a monocular camera mounted onto the gripper of a collaborative robot. We discuss and propose a solution to the pose space conversion problem. Finally, we present several criteria to analyze the 3D reconstruction accuracy. These could be used as guidelines to improve the accuracy of 3D reconstructions with monocular LSD-SLAM and other SLAM based solutions.
Tasks	3D Reconstruction, Motion Planning, Robot Navigation
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02257v1
PDF	http://arxiv.org/pdf/1803.02257v1.pdf
PWC	https://paperswithcode.com/paper/methodology-to-analyze-the-accuracy-of-3d
Repo
Framework

Robust Sparse Reduced Rank Regression in High Dimensions


Title	Robust Sparse Reduced Rank Regression in High Dimensions
Authors	Kean Ming Tan, Qiang Sun, Daniela Witten
Abstract	We propose robust sparse reduced rank regression for analyzing large and complex high-dimensional data with heavy-tailed random noise. The proposed method is based on a convex relaxation of a rank- and sparsity-constrained non-convex optimization problem, which is then solved using the alternating direction method of multipliers algorithm. We establish non-asymptotic estimation error bounds under both Frobenius and nuclear norms in the high-dimensional setting. This is a major contribution over existing results in reduced rank regression, which mainly focus on rank selection and prediction consistency. Our theoretical results quantify the tradeoff between heavy-tailedness of the random noise and statistical bias. For random noise with bounded $(1+\delta)$th moment with $\delta \in (0,1)$, the rate of convergence is a function of $\delta$, and is slower than the sub-Gaussian-type deviation bounds; for random noise with bounded second moment, we obtain a rate of convergence as if sub-Gaussian noise were assumed. Furthermore, the transition between the two regimes is smooth. We illustrate the performance of the proposed method via extensive numerical studies and a data application.
Tasks
Published	2018-10-18
URL	http://arxiv.org/abs/1810.07913v2
PDF	http://arxiv.org/pdf/1810.07913v2.pdf
PWC	https://paperswithcode.com/paper/distributionally-robust-reduced-rank
Repo
Framework

Vision-based Pose Estimation for Augmented Reality : A Comparison Study


Title	Vision-based Pose Estimation for Augmented Reality : A Comparison Study
Authors	Hayet Belghit, Abdelkader Bellarbi, Nadia Zenati, Samir Otmane
Abstract	Augmented reality aims to enrich our real world by inserting 3D virtual objects. In order to accomplish this goal, it is important that virtual elements are rendered and aligned in the real scene in an accurate and visually acceptable way. The solution of this problem can be related to a pose estimation and 3D camera localization. This paper presents a survey on different approaches of 3D pose estimation in augmented reality and gives classification of key-points-based techniques. The study given in this paper may help both developers and researchers in the field of augmented reality.
Tasks	3D Pose Estimation, Camera Localization, Pose Estimation
Published	2018-06-25
URL	http://arxiv.org/abs/1806.09316v1
PDF	http://arxiv.org/pdf/1806.09316v1.pdf
PWC	https://paperswithcode.com/paper/vision-based-pose-estimation-for-augmented
Repo
Framework

zoNNscan : a boundary-entropy index for zone inspection of neural models


Title	zoNNscan : a boundary-entropy index for zone inspection of neural models
Authors	Adel Jaouen, Erwan Le Merrer
Abstract	The training of deep neural network classifiers results in decision boundaries which geometry is still not well understood. This is in direct relation with classification problems such as so called adversarial examples. We introduce zoNNscan, an index that is intended to inform on the boundary uncertainty (in terms of the presence of other classes) around one given input datapoint. It is based on confidence entropy, and is implemented through sampling in the multidimensional ball surrounding that input. We detail the zoNNscan index, give an algorithm for approximating it, and finally illustrate its benefits on four applications, including two important problems for the adoption of deep networks in critical systems: adversarial examples and corner case inputs. We highlight that zoNNscan exhibits significantly higher values than for standard inputs in those two problem classes.
Tasks
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06797v1
PDF	http://arxiv.org/pdf/1808.06797v1.pdf
PWC	https://paperswithcode.com/paper/zonnscan-a-boundary-entropy-index-for-zone
Repo
Framework

Mining Contrasting Quasi-Clique Patterns


Title	Mining Contrasting Quasi-Clique Patterns
Authors	Roberto Alonso, Stephan Günnemann
Abstract	Mining dense quasi-cliques is a well-known clustering task with applications ranging from social networks over collaboration graphs to document analysis. Recent work has extended this task to multiple graphs; i.e. the goal is to find groups of vertices highly dense among multiple graphs. In this paper, we argue that in a multi-graph scenario the sparsity is valuable for knowledge extraction as well. We introduce the concept of contrasting quasi-clique patterns: a collection of vertices highly dense in one graph but highly sparse (i.e. less connected) in a second graph. Thus, these patterns specifically highlight the difference/contrast between the considered graphs. Based on our novel model, we propose an algorithm that enables fast computation of contrasting patterns by exploiting intelligent traversal and pruning techniques. We showcase the potential of contrasting patterns on a variety of synthetic and real-world datasets.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01836v1
PDF	http://arxiv.org/pdf/1810.01836v1.pdf
PWC	https://paperswithcode.com/paper/mining-contrasting-quasi-clique-patterns
Repo
Framework