January 31, 2020

3005 words 15 mins read

Paper Group ANR 34

Explaining Deep Learning Models with Constrained Adversarial Examples. Overview of the Ugglan Entity Discovery and Linking System. Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks. Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions. DCDB Wintermute: Enabling Online and Holistic Operational Data Analytics …

Explaining Deep Learning Models with Constrained Adversarial Examples


Title	Explaining Deep Learning Models with Constrained Adversarial Examples
Authors	Jonathan Moore, Nils Hammerla, Chris Watkins
Abstract	Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of explaining why a particular classification was made explain how a different outcome can be achieved. This gives the recipients of the explanation a better way to understand the outcome, and provides an actionable suggestion. We show that the introduced method of Constrained Adversarial Examples (CADEX) can be used in real world applications, and yields explanations which incorporate business or domain constraints such as handling categorical attributes and range constraints.
Tasks
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10671v1
PDF	https://arxiv.org/pdf/1906.10671v1.pdf
PWC	https://paperswithcode.com/paper/explaining-deep-learning-models-with
Repo
Framework

Overview of the Ugglan Entity Discovery and Linking System


Title	Overview of the Ugglan Entity Discovery and Linking System
Authors	Marcus Klang, Firas Dib, Pierre Nugues
Abstract	Ugglan is a system designed to discover named entities and link them to unique identifiers in a knowledge base. It is based on a combination of a name and nominal dictionary derived from Wikipedia and Wikidata, a named entity recognition module (NER) using fixed ordinally-forgetting encoding (FOFE) trained on the TAC EDL data from 2014-2016, a candidate generation module from the Wikipedia link graph across multiple editions, a PageRank link and cooccurrence graph disambiguator, and finally a reranker trained on the TAC EDL 2015-2016 data.
Tasks	Named Entity Recognition
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05498v1
PDF	http://arxiv.org/pdf/1903.05498v1.pdf
PWC	https://paperswithcode.com/paper/overview-of-the-ugglan-entity-discovery-and
Repo
Framework

Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks


Title	Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks
Authors	Sumant Sharma, Simone D’Amico
Abstract	This work introduces the Spacecraft Pose Network (SPN) for on-board estimation of the pose, i.e., the relative position and attitude, of a known non-cooperative spacecraft using monocular vision. In contrast to other state-of-the-art pose estimation approaches for spaceborne applications, the SPN method does not require the formulation of hand-engineered features and only requires a single grayscale image to determine the pose of the spacecraft relative to the camera. The SPN method uses a Convolutional Neural Network (CNN) with three branches to solve for the pose. The first branch of the CNN bootstraps a state-of-the-art object detector to detect a 2D bounding box around the target spacecraft. The region inside the bounding box is then used by the other two branches of the CNN to determine the attitude by initially classifying the input region into discrete coarse attitude labels before regressing to a finer estimate. The SPN method then uses a novel Gauss-Newton algorithm to estimate the position by using the constraints imposed by the detected 2D bounding box and the estimated attitude. The secondary contribution of this work is the generation of the Spacecraft PosE Estimation Dataset (SPEED). SPEED consists of synthetic as well as actual camera images of a mock-up of the Tango spacecraft from the PRISMA mission. The synthetic images are created by fusing OpenGL-based renderings of the spacecraft’s 3D model with actual images of the Earth captured by the Himawari-8 meteorological satellite. The actual camera images are created using a 7 degrees-of-freedom robotic arm, which positions and orients a vision-based sensor with respect to a full-scale mock-up of the Tango spacecraft. The SPN method, trained only on synthetic images, produces degree-level attitude error and cm-level position errors when evaluated on the actual camera images not used during training.
Tasks	Pose Estimation
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09868v1
PDF	https://arxiv.org/pdf/1906.09868v1.pdf
PWC	https://paperswithcode.com/paper/pose-estimation-for-non-cooperative-1
Repo
Framework

Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions


Title	Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions
Authors	Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla, Vishal M. Patel
Abstract	Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images. To address this issue, we propose an unsupervised prior-based domain adversarial object detection framework for adapting the detectors to hazy and rainy conditions. Motivated by these, we use weather-specific prior knowledge obtained using the principles of image formation to define a novel prior-adversarial loss. The prior-adversarial loss used to train the adaptation process aims to reduce the weather-specific information in the features, thereby mitigating the effects of weather on the detection performance. Additionally, we introduce a set of residual feature recovery blocks in the object detection pipeline to de-distort the feature space, resulting in further improvements. Evaluations performed on various datasets (Foggy-Cityscapes, Rainy-Cityscapes, RTTS and UFDD) for different conditions (like haze, rain) demonstrates the effectiveness of the proposed approach.
Tasks	Object Detection
Published	2019-11-29
URL	https://arxiv.org/abs/1912.00070v2
PDF	https://arxiv.org/pdf/1912.00070v2.pdf
PWC	https://paperswithcode.com/paper/prior-based-domain-adaptive-object-detection
Repo
Framework

DCDB Wintermute: Enabling Online and Holistic Operational Data Analytics on HPC Systems


Title	DCDB Wintermute: Enabling Online and Holistic Operational Data Analytics on HPC Systems
Authors	Alessio Netti, Micha Mueller, Carla Guillen, Michael Ott, Daniele Tafani, Gence Ozer, Martin Schulz
Abstract	The complexity of today’s HPC systems increases as we move closer to the exascale goal, raising concerns about their sustainability. In an effort to improve their efficiency and effectiveness, more and more HPC installations are experimenting with fine-grained monitoring coupled with Operational Data Analytics (ODA) to drive resource management decisions. However, while monitoring is an established reality in HPC, no generic framework exists to enable holistic and online operational data analytics, leading to insular ad-hoc solutions each addressing only specific aspects of the problem. In this paper we propose Wintermute, a novel operational data analytics framework for HPC installations, built upon the holistic DCDB monitoring system. Wintermute is designed following a survey of common operational requirements, and as such offers a large variety of configuration options to accommodate these varying requirements. Moreover, Wintermute is based on a set of logical abstractions to ease the configuration of models at a large scale and maximize code re-use. We highlight Wintermute’s flexibility through a series of case studies, each targeting a different aspect of the management of HPC systems, and demonstrate its small resource footprint.
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06156v1
PDF	https://arxiv.org/pdf/1910.06156v1.pdf
PWC	https://paperswithcode.com/paper/dcdb-wintermute-enabling-online-and-holistic
Repo
Framework

Guided Random Forest and its application to data approximation


Title	Guided Random Forest and its application to data approximation
Authors	Prashant Gupta, Aashi Jindal, Jayadeva, Debarka Sengupta
Abstract	We present a new way of constructing an ensemble classifier, named the Guided Random Forest (GRAF) in the sequel. GRAF extends the idea of building oblique decision trees with localized partitioning to obtain a global partitioning. We show that global partitioning bridges the gap between decision trees and boosting algorithms. We empirically demonstrate that global partitioning reduces the generalization error bound. Results on 115 benchmark datasets show that GRAF yields comparable or better results on a majority of datasets. We also present a new way of approximating the datasets in the framework of random forests.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00659v1
PDF	https://arxiv.org/pdf/1909.00659v1.pdf
PWC	https://paperswithcode.com/paper/guided-random-forest-and-its-application-to
Repo
Framework

Radar Human Motion Recognition Using Motion States and Two-Way Classifications


Title	Radar Human Motion Recognition Using Motion States and Two-Way Classifications
Authors	Moeness G. Amin, Ronny G. Guendel
Abstract	We perform classification of activities of daily living (ADL) using a Frequency-Modulated Continuous Waveform (FMCW) radar. In particular, we consider contiguous motions that are inseparable in time. Both the micro-Doppler signature and range-map are used to determine transitions from translation (walking) to in-place motions and vice versa, as well as to provide motion onset and the offset times. The possible classes of activities post and prior to the translation motion can be separately handled by forward and background classifiers. The paper describes ADL in terms of states and transitioning actions, and sets a framework to deal with separable and inseparable contiguous motions. It is shown that considering only the physically possible classes of motions stemming from the current motion state improves classification rates compared to incorporating all ADL for any given time.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03512v1
PDF	https://arxiv.org/pdf/1911.03512v1.pdf
PWC	https://paperswithcode.com/paper/radar-human-motion-recognition-using-motion
Repo
Framework

HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings


Title	HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings
Authors	Saba Anwar, Dmitry Ustalov, Nikolay Arefyev, Simone Paolo Ponzetto, Chris Biemann, Alexander Panchenko
Abstract	We present our system for semantic frame induction that showed the best performance in Subtask B.1 and finished as the runner-up in Subtask A of the SemEval 2019 Task 2 on unsupervised semantic frame induction (QasemiZadeh et al., 2019). Our approach separates this task into two independent steps: verb clustering using word and their context embeddings and role labeling by combining these embeddings with syntactical features. A simple combination of these steps shows very competitive results and can be extended to process other datasets and languages.
Tasks	Word Embeddings
Published	2019-05-05
URL	https://arxiv.org/abs/1905.01739v1
PDF	https://arxiv.org/pdf/1905.01739v1.pdf
PWC	https://paperswithcode.com/paper/hhmm-at-semeval-2019-task-2-unsupervised
Repo
Framework

The Prevalence of Errors in Machine Learning Experiments


Title	The Prevalence of Errors in Machine Learning Experiments
Authors	Martin Shepperd, Yuchen Guo, Ning Li, Mahir Arzoky, Andrea Capiluppi, Steve Counsell, Giuseppe Destefanis, Stephen Swift, Allan Tucker, Leila Yousefi
Abstract	Context: Conducting experiments is central to research machine learning research to benchmark, evaluate and compare learning algorithms. Consequently it is important we conduct reliable, trustworthy experiments. Objective: We investigate the incidence of errors in a sample of machine learning experiments in the domain of software defect prediction. Our focus is simple arithmetical and statistical errors. Method: We analyse 49 papers describing 2456 individual experimental results from a previously undertaken systematic review comparing supervised and unsupervised defect prediction classifiers. We extract the confusion matrices and test for relevant constraints, e.g., the marginal probabilities must sum to one. We also check for multiple statistical significance testing errors. Results: We find that a total of 22 out of 49 papers contain demonstrable errors. Of these 7 were statistical and 16 related to confusion matrix inconsistency (one paper contained both classes of error). Conclusions: Whilst some errors may be of a relatively trivial nature, e.g., transcription errors their presence does not engender confidence. We strongly urge researchers to follow open science principles so errors can be more easily be detected and corrected, thus as a community reduce this worryingly high error rate with our computational experiments.
Tasks
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04436v1
PDF	https://arxiv.org/pdf/1909.04436v1.pdf
PWC	https://paperswithcode.com/paper/the-prevalence-of-errors-in-machine-learning
Repo
Framework

Accelerated Information Gradient flow


Title	Accelerated Information Gradient flow
Authors	Yifei Wang, Wuchen Li
Abstract	We present a systematic framework for the Nesterov’s accelerated gradient flows in the spaces of probabilities embedded with information metrics. Here two metrics are considered, including both the Fisher-Rao metric and the Wasserstein-$2$ metric. For the Wasserstein-$2$ metric case, we prove the convergence properties of the accelerated gradient flows, and introduce their formulations in Gaussian families. Furthermore, we propose a practical discrete-time algorithm in particle implementations with an adaptive restart technique. We formulate a novel bandwidth selection method, which learns the Wasserstein-$2$ gradient direction from Brownian-motion samples. Experimental results including Bayesian inference show the strength of the current method compared with the state-of-the-art.
Tasks	Bayesian Inference
Published	2019-09-04
URL	https://arxiv.org/abs/1909.02102v1
PDF	https://arxiv.org/pdf/1909.02102v1.pdf
PWC	https://paperswithcode.com/paper/accelerated-information-gradient-flow
Repo
Framework

Distribution of residual autocorrelations for multiplicative seasonal ARMA models with uncorrelated but non-independent error terms


Title	Distribution of residual autocorrelations for multiplicative seasonal ARMA models with uncorrelated but non-independent error terms
Authors	Yacouba Boubacar Maïnassara, Abdoulkarim Ilmi Amir
Abstract	In this paper we consider portmanteau tests for testing the adequacy of multiplicative seasonal autoregressive moving-average (SARMA) models under the assumption that the errors are uncorrelated but not necessarily independent.We relax the standard independence assumption on the error term in order to extend the range of application of the SARMA models.We study the asymptotic distributions of residual and normalized residual empirical autocovariances and autocorrelations underweak assumptions on the noise. We establish the asymptotic behaviour of the proposed statistics. A set of Monte Carlo experiments and an application to monthly mean total sunspot number are presented.
Tasks
Published	2019-02-08
URL	http://arxiv.org/abs/1902.03000v1
PDF	http://arxiv.org/pdf/1902.03000v1.pdf
PWC	https://paperswithcode.com/paper/distribution-of-residual-autocorrelations-for
Repo
Framework

All You Need is Ratings: A Clustering Approach to Synthetic Rating Datasets Generation


Title	All You Need is Ratings: A Clustering Approach to Synthetic Rating Datasets Generation
Authors	Diego Monti, Giuseppe Rizzo, Maurizio Morisio
Abstract	The public availability of collections containing user preferences is of vital importance for performing offline evaluations in the field of recommender systems. However, the number of rating datasets is limited because of the costs required for their creation and the fear of violating the privacy of the users by sharing them. For this reason, numerous research attempts investigated the creation of synthetic collections of ratings using generative approaches. Nevertheless, these datasets are usually not reliable enough for conducting an evaluation campaign. In this paper, we propose a method for creating synthetic datasets with a configurable number of users that mimic the characteristics of already existing ones. We empirically validated the proposed approach by exploiting the synthetic datasets for evaluating different recommenders and by comparing the results with the ones obtained using real datasets.
Tasks	Recommendation Systems
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00687v1
PDF	https://arxiv.org/pdf/1909.00687v1.pdf
PWC	https://paperswithcode.com/paper/all-you-need-is-ratings-a-clustering-approach
Repo
Framework

Submodular Maximization under Fading Model: Building Online Quizzes for Better Customer Segmentation


Title	Submodular Maximization under Fading Model: Building Online Quizzes for Better Customer Segmentation
Authors	Shaojie Tang
Abstract	E-Commerce personalization aims to provide individualized offers, product recommendations, and other content to customers based on their interests. The foundation of any personalization effort is customer segmentation. The idea of customer segmentation is to group customers together according to identifiable segmentation attributes including geolocation, gender, age, and interests. Personality quiz turns out to be a powerful tool that enables costumer segmentation by actively asking them questions, and marketers are using it as an effective method of generating leads and increasing e-commerce sales. In this paper, we study the problem of how to select and sequence a group of quiz questions so as to optimize the quality of customer segmentation. In particular, we use conditional entropy to measure the utility of a given group of quiz questions. We model the user behavior when interacting with a sequence of quiz questions as a Markov process. Then we develop a series of question allocation strategies with provable performance bound.
Tasks
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07708v2
PDF	http://arxiv.org/pdf/1901.07708v2.pdf
PWC	https://paperswithcode.com/paper/submodular-maximization-under-fading-model
Repo
Framework

Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge


Title	Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge
Authors	Xiahai Zhuang, Lei Li, Christian Payer, Darko Stern, Martin Urschler, Mattias P. Heinrich, Julien Oster, Chunliang Wang, Orjan Smedby, Cheng Bian, Xin Yang, Pheng-Ann Heng, Aliasghar Mortazi, Ulas Bagci, Guanyu Yang, Chenchen Sun, Gaetan Galisot, Jean-Yves Ramel, Thierry Brouard, Qianqian Tong, Weixin Si, Xiangyun Liao, Guodong Zeng, Zenglin Shi, Guoyan Zheng, Chengjia Wang, Tom MacGillivray, David Newby, Kawal Rhode, Sebastien Ourselin, Raad Mohiaddin, Jennifer Keegan, David Firmin, Guang Yang
Abstract	Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be arduous due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, a set of training data is generally needed for constructing priors or for training. In addition, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provides 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results show that many of the deep learning (DL) based methods achieved high accuracy, even though the number of training datasets was limited. A number of them also reported poor results in the blinded evaluation, probably due to overfitting in their training. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated robust and stable performance, even though the accuracy is not as good as the best DL method in CT segmentation. The challenge, including the provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (\url{www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mmwhs/}).
Tasks
Published	2019-02-21
URL	http://arxiv.org/abs/1902.07880v1
PDF	http://arxiv.org/pdf/1902.07880v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-algorithms-for-multi-modality
Repo
Framework

Sizing of a PV/Battery System Through Stochastic Control and Plant Aggregation


Title	Sizing of a PV/Battery System Through Stochastic Control and Plant Aggregation
Authors	Thomas Carriere, Christophe Vernay, Sebastien Pitaval, Franccois-Pascal Neirac, George Kariniotakis
Abstract	The objective of this work is to reduce the storage dimensions required to operate a coupled photovoltaic (PV) and Battery Energy Storage System (BESS) in an electricity market, while keeping the same level of performance. Performance is measured either with the amount of errors between the energy sold on the market and the actual generation of the PV/BESS i.e. the imbalance, or directly with the revenue generated on the electricity market from the PV/BESS operation. Two solutions are proposed and tested to reduce the BESS size requirement. The first solution is to participate in electricity markets with an aggregation of several plants instead of a single plant, which effectively reduces the uncertainty of the PV power generation. The second is to participate in an intra-day market to reduce the BESS usage. To evaluate the effects of these two solutions on the BESS size requirement, we simulate the control of the PV/BESS system in an electricity market.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06828v1
PDF	https://arxiv.org/pdf/1910.06828v1.pdf
PWC	https://paperswithcode.com/paper/sizing-of-a-pvbattery-system-through
Repo
Framework