October 19, 2019

3154 words 15 mins read

Paper Group ANR 398

Gaussian Word Embedding with a Wasserstein Distance Loss. Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks. Learning From Positive and Unlabeled Data: A Survey. Mobility Mode Detection Using WiFi Signals. The closed loop between opinion formation and personalised recommendations. Multi-task learning of daily wor …

Gaussian Word Embedding with a Wasserstein Distance Loss


Title	Gaussian Word Embedding with a Wasserstein Distance Loss
Authors	Chi Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang
Abstract	Compared with word embedding based on point representation, distribution-based word embedding shows more flexibility in expressing uncertainty and therefore embeds richer semantic information when representing words. The Wasserstein distance provides a natural notion of dissimilarity with probability measures and has a closed-form solution when measuring the distance between two Gaussian distributions. Therefore, with the aim of representing words in a highly efficient way, we propose to operate a Gaussian word embedding model with a loss function based on the Wasserstein distance. Also, external information from ConceptNet will be used to semi-supervise the results of the Gaussian word embedding. Thirteen datasets from the word similarity task, together with one from the word entailment task, and six datasets from the downstream document classification task will be evaluated in this paper to test our hypothesis.
Tasks	Document Classification
Published	2018-08-21
URL	http://arxiv.org/abs/1808.07016v7
PDF	http://arxiv.org/pdf/1808.07016v7.pdf
PWC	https://paperswithcode.com/paper/gaussian-word-embedding-with-a-wasserstein
Repo
Framework

Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks


Title	Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
Authors	Yulei Qin, Juan Wen, Hao Zheng, Xiaolin Huang, Jie Yang, Ning Song, Yue-Min Zhu, Lingqian Wu, Guang-Zhong Yang
Abstract	Chromosome classification is critical for karyotyping in abnormality diagnosis. To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome’s type and polarity using deep convolutional networks. The approach consists of one global-scale network (G-Net) and one local-scale network (L-Net). It follows three stages. The first stage is to learn both global and local features. We extract global features and detect finer local regions via the G-Net. By proposing a varifocal mechanism, we zoom into local parts and extract local features via the L-Net. Residual learning and multi-task learning strategies are utilized to promote high-level feature extraction. The detection of discriminative local parts is fulfilled by a localization subnet of the G-Net, whose training process involves both supervised and weakly-supervised learning. The second stage is to build two multi-layer perceptron classifiers that exploit features of both two scales to boost classification performance. The third stage is to introduce a dispatch strategy of assigning each chromosome to a type within each patient case, by utilizing the domain knowledge of karyotyping. Evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) 99.2 for both type and polarity tasks. It outperformed state-of-the-art methods, demonstrating the effectiveness of our varifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The proposed method has been applied to assist practical karyotype diagnosis.
Tasks	Multi-Task Learning
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05943v4
PDF	http://arxiv.org/pdf/1810.05943v4.pdf
PWC	https://paperswithcode.com/paper/varifocal-net-a-chromosome-classification
Repo
Framework

Learning From Positive and Unlabeled Data: A Survey


Title	Learning From Positive and Unlabeled Data: A Survey
Authors	Jessa Bekker, Jesse Davis
Abstract	Learning from positive and unlabeled data or PU learning is the setting where a learner only has access to positive examples and unlabeled data. The assumption is that the unlabeled data can contain both positive and negative examples. This setting has attracted increasing interest within the machine learning literature as this type of data naturally arises in applications such as medical diagnosis and knowledge base completion. This article provides a survey of the current state of the art in PU learning. It proposes seven key research questions that commonly arise in this field and provides a broad overview of how the field has tried to address them.
Tasks	Knowledge Base Completion, Medical Diagnosis
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04820v1
PDF	http://arxiv.org/pdf/1811.04820v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-positive-and-unlabeled-data-a
Repo
Framework

Mobility Mode Detection Using WiFi Signals


Title	Mobility Mode Detection Using WiFi Signals
Authors	Arash Kalatian, Bilal Farooq
Abstract	We utilize Wi-Fi communications from smartphones to predict their mobility mode, i.e. walking, biking and driving. Wi-Fi sensors were deployed at four strategic locations in a closed loop on streets in downtown Toronto. Deep neural network (Multilayer Perceptron) along with three decision tree based classifiers (Decision Tree, Bagged Decision Tree and Random Forest) are developed. Results show that the best prediction accuracy is achieved by Multilayer Perceptron, with 86.52% correct predictions of mobility modes.
Tasks
Published	2018-09-16
URL	http://arxiv.org/abs/1809.05788v1
PDF	http://arxiv.org/pdf/1809.05788v1.pdf
PWC	https://paperswithcode.com/paper/mobility-mode-detection-using-wifi-signals
Repo
Framework

The closed loop between opinion formation and personalised recommendations


Title	The closed loop between opinion formation and personalised recommendations
Authors	Wilbert Samuel Rossi, Jan Willem Polderman, Paolo Frasca
Abstract	In online platforms, recommender systems are responsible for directing users to relevant contents. In order to enhance the users’ engagement, recommender systems adapt their output to the reactions of the users, who are in turn affected by the recommended contents. In this work, we study a tractable analytical model of a user that interacts with an online news aggregator, with the purpose of making explicit the feedback loop between the evolution of the user’s opinion and the personalised recommendation of contents. More specifically, we assume that the user is endowed with a scalar opinion about a certain issue and seeks news about it on a news aggregator: this opinion is influenced by all received news, which are characterized by a binary position on the issue at hand. The user is affected by a confirmation bias, that is, a preference for news that confirm her current opinion. The news aggregator recommends items with the goal of maximizing the number of user’s clicks (as a measure of her engagement): in order to fulfil its goal, the recommender has to compromise between exploring the user’s preferences and exploiting what it has learned so far. After defining suitable metrics for the effectiveness of the recommender systems (such as the click-through rate) and for its impact on the opinion, we perform both extensive numerical simulations and a mathematical analysis of the model. We find that personalised recommendations markedly affect the evolution of opinions and favor the emergence of more extreme ones: the intensity of these effects is inherently related to the effectiveness of the recommender. We also show that by tuning the amount of randomness in the recommendation algorithm, one can seek a balance between the effectiveness of the recommendation system and its impact on the opinions.
Tasks	Recommendation Systems
Published	2018-09-12
URL	https://arxiv.org/abs/1809.04644v2
PDF	https://arxiv.org/pdf/1809.04644v2.pdf
PWC	https://paperswithcode.com/paper/the-closed-loop-between-opinion-formation-and
Repo
Framework

Multi-task learning of daily work and study round-trips from survey data


Title	Multi-task learning of daily work and study round-trips from survey data
Authors	Mehdi Katranji, Sami Kraiem, Laurent Moalic, Guilhem Sanmarty, Alexandre Caminada, Fouad Hadj Selem
Abstract	In this study, we present a machine learning approach to infer the worker and student mobility flows on daily basis from static censuses. The rapid urbanization has made the estimation of the human mobility flows a critical task for transportation and urban planners. The primary objective of this paper is to complete individuals’ census data with working and studying trips, allowing its merging with other mobility data to better estimate the complete origin-destination matrices. Worker and student mobility flows are among the most weekly regular displacements and consequently generate road congestion problems. Estimating their round-trips eases the decision-making processes for local authorities. Worker and student censuses often contain home location, work places and educational institutions. We thus propose a neural network model that learns the temporal distribution of displacements from other mobility sources and tries to predict them on new censuses data. The inclusion of multi-task learning in our neural network results in a significant error rate control in comparison to single task learning.
Tasks	Decision Making, Multi-Task Learning
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03903v1
PDF	http://arxiv.org/pdf/1806.03903v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-of-daily-work-and-study
Repo
Framework

Inferring Point Clouds from Single Monocular Images by Depth Intermediation


Title	Inferring Point Clouds from Single Monocular Images by Depth Intermediation
Authors	Wei Zeng, Sezer Karaoglu, Theo Gevers
Abstract	In this paper, we propose a framework for generating 3D point cloud of an object from a single-view RGB image. Most previous work predict the 3D point coordinates from single RGB images directly. We decompose this problem into depth estimation from single images and point completion from partial point clouds. Our method sequentially predicts the depth maps and then infers the complete 3D object point clouds based on the predicted partial point clouds. We explicitly impose the camera model geometrical constraint in our pipeline and enforce the alignment of the generated point clouds and estimated depth maps. Experimental results for the single image 3D object reconstruction task show that the proposed method outperforms state-of-the-art methods. Both the qualitative and quantitative results demonstrate the generality and suitability of our method.
Tasks	3D Object Reconstruction, Depth Estimation, Object Reconstruction
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01402v2
PDF	http://arxiv.org/pdf/1812.01402v2.pdf
PWC	https://paperswithcode.com/paper/inferring-point-clouds-from-single-monocular
Repo
Framework

Evidential community detection based on density peaks


Title	Evidential community detection based on density peaks
Authors	Kuang Zhou, Quan Pan, Arnaud Martin
Abstract	Credal partitions in the framework of belief functions can give us a better understanding of the analyzed data set. In order to find credal community structure in graph data sets, in this paper, we propose a novel evidential community detection algorithm based on density peaks (EDPC). Two new metrics, the local density $\rho$ and the minimum dissimi-larity $\delta$, are first defined for each node in the graph. Then the nodes with both higher $\rho$ and $\delta$ values are identified as community centers. Finally, the remaing nodes are assigned with corresponding community labels through a simple two-step evidential label propagation strategy. The membership of each node is described in the form of basic belief assignments , which can well express the uncertainty included in the community structure of the graph. The experiments demonstrate the effectiveness of the proposed method on real-world networks.
Tasks	Community Detection
Published	2018-09-28
URL	http://arxiv.org/abs/1809.10903v1
PDF	http://arxiv.org/pdf/1809.10903v1.pdf
PWC	https://paperswithcode.com/paper/evidential-community-detection-based-on
Repo
Framework

Reproduction Report on “Learn to Pay Attention”


Title	Reproduction Report on “Learn to Pay Attention”
Authors	Levan Shugliashvili, Davit Soselia, Shota Amashukeli, Irakli Koberidze
Abstract	We have successfully implemented the “Learn to Pay Attention” model of attention mechanism in convolutional neural networks, and have replicated the results of the original paper in the categories of image classification and fine-grained recognition.
Tasks	Image Classification
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04650v1
PDF	http://arxiv.org/pdf/1812.04650v1.pdf
PWC	https://paperswithcode.com/paper/reproduction-report-on-learn-to-pay-attention
Repo
Framework

Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and its Variance Estimate


Title	Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and its Variance Estimate
Authors	Indrayudh Ghosal, Giles Hooker
Abstract	In this paper we propose using the principle of boosting to reduce the bias of a random forest prediction in the regression setting. From the original random forest fit we extract the residuals and then fit another random forest to these residuals. We call the sum of these two random forests a one-step boosted forest. We show with simulated and real data that the one-step boosted forest has a reduced bias compared to the original random forest. The paper also provides a variance estimate of the one-step boosted forest by an extension of the infinitesimal Jackknife estimator. Using this variance estimate we can construct prediction intervals for the boosted forest and we show that they have good coverage probabilities. Combining the bias reduction and the variance estimate we show that the one-step boosted forest has a significant reduction in predictive mean squared error and thus an improvement in predictive performance. When applied on datasets from the UCI database, one-step boosted forest performs better than random forest and gradient boosting machine algorithms. Theoretically we can also extend such a boosting process to more than one step and the same principles outlined in this paper can be used to find variance estimates for such predictors. Such boosting will reduce bias even further but it risks over-fitting and also increases the computational burden.
Tasks
Published	2018-03-21
URL	http://arxiv.org/abs/1803.08000v2
PDF	http://arxiv.org/pdf/1803.08000v2.pdf
PWC	https://paperswithcode.com/paper/boosting-random-forests-to-reduce-bias-one
Repo
Framework

Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection


Title	Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection
Authors	Yancheng Bai, Huijuan Xu, Kate Saenko, Bernard Ghanem
Abstract	Activity detection is a fundamental problem in computer vision. Detecting activities of different temporal scales is particularly challenging. In this paper, we propose the contextual multi-scale region convolutional 3D network (CMS-RC3D) for activity detection. To deal with the inherent temporal scale variability of activity instances, the temporal feature pyramid is used to represent activities of different temporal scales. On each level of the temporal feature pyramid, an activity proposal detector and an activity classifier are learned to detect activities of specific temporal scales. Temporal contextual information is fused into activity classifiers for better recognition. More importantly, the entire model at all levels can be trained end-to-end. Our CMS-RC3D detector can deal with activities at all temporal scale ranges with only a single pass through the backbone network. We test our detector on two public activity detection benchmarks, THUMOS14 and ActivityNet. Extensive experiments show that the proposed CMS-RC3D detector outperforms state-of-the-art methods on THUMOS14 by a substantial margin and achieves comparable results on ActivityNet despite using a shallow feature extractor.
Tasks	Action Detection, Activity Detection
Published	2018-01-28
URL	http://arxiv.org/abs/1801.09184v1
PDF	http://arxiv.org/pdf/1801.09184v1.pdf
PWC	https://paperswithcode.com/paper/contextual-multi-scale-region-convolutional
Repo
Framework

Global optimization of expensive black-box models based on asynchronous hybrid-criterion with interval reduction


Title	Global optimization of expensive black-box models based on asynchronous hybrid-criterion with interval reduction
Authors	Chunlin Gong, Xu Li, Hua Su, Jinlei Guo, Liangxian Gu
Abstract	In this paper, a new sequential surrogate-based optimization (SSBO) algorithm is developed, which aims to improve the global search ability and local search efficiency for the global optimization of expensive black-box models. The proposed method involves three basic sub-criteria to infill new samples asynchronously to balance the global exploration and local exploitation. First, to capture the promising possible global optimal region, searching for the global optimum with genetic algorithm (GA) based on the current surrogate models of the objective and constraint functions. Second, to infill samples in the region with sparse samples to improve the global accuracy of the surrogate models, a grid searching with Latin hypercube sampling (LHS) with the current surrogate model is adopted to explore the sample space. Third, to accelerate the local searching efficiency, searching for a local optimum with sequential quadratic programming (SQP) based on the local surrogate models in the reduced interval, which involves some samples near the current optimum. When the new sample is too close to the existing ones, the new sample should be abandoned, due to the poor additional information. According to the three sub-criteria, the new samples are placed in the regions which have not been fully explored and includes the possible global optimum point. When a possible global optimum point is found, the local searching sub-criterion captures the local optimum around it rapidly. Numerical and engineering examples are used to verify the efficiency of the proposed method. The statistical results show that the proposed method has good global searching ability and efficiency.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12142v1
PDF	http://arxiv.org/pdf/1811.12142v1.pdf
PWC	https://paperswithcode.com/paper/global-optimization-of-expensive-black-box
Repo
Framework

BoxNet: Deep Learning Based Biomedical Image Segmentation Using Boxes Only Annotation


Title	BoxNet: Deep Learning Based Biomedical Image Segmentation Using Boxes Only Annotation
Authors	Lin Yang, Yizhe Zhang, Zhuo Zhao, Hao Zheng, Peixian Liang, Michael T. C. Ying, Anil T. Ahuja, Danny Z. Chen
Abstract	In recent years, deep learning (DL) methods have become powerful tools for biomedical image segmentation. However, high annotation efforts and costs are commonly needed to acquire sufficient biomedical training data for DL models. To alleviate the burden of manual annotation, in this paper, we propose a new weakly supervised DL approach for biomedical image segmentation using boxes only annotation. First, we develop a method to combine graph search (GS) and DL to generate fine object masks from box annotation, in which DL uses box annotation to compute a rough segmentation for GS and then GS is applied to locate the optimal object boundaries. During the mask generation process, we carefully utilize information from box annotation to filter out potential errors, and then use the generated masks to train an accurate DL segmentation network. Extensive experiments on gland segmentation in histology images, lymph node segmentation in ultrasound images, and fungus segmentation in electron microscopy images show that our approach attains superior performance over the best known state-of-the-art weakly supervised DL method and is able to achieve (1) nearly the same accuracy compared to fully supervised DL methods with far less annotation effort, (2) significantly better results with similar annotation time, and (3) robust performance in various applications.
Tasks	Semantic Segmentation
Published	2018-06-02
URL	http://arxiv.org/abs/1806.00593v1
PDF	http://arxiv.org/pdf/1806.00593v1.pdf
PWC	https://paperswithcode.com/paper/boxnet-deep-learning-based-biomedical-image
Repo
Framework

Quantized-Dialog Language Model for Goal-Oriented Conversational Systems


Title	Quantized-Dialog Language Model for Goal-Oriented Conversational Systems
Authors	R. Chulaka Gunasekara, David Nahamoo, Lazaros C. Polymenakos, Jatin Ganhotra, Kshitij P. Fadnis
Abstract	We propose a novel methodology to address dialog learning in the context of goal-oriented conversational systems. The key idea is to quantize the dialog space into clusters and create a language model across the clusters, thus allowing for an accurate choice of the next utterance in the conversation. The language model relies on n-grams associated with clusters of utterances. This quantized-dialog language model methodology has been applied to the end-to-end goal-oriented track of the latest Dialog System Technology Challenges (DSTC6). The objective is to find the correct system utterance from a pool of candidates in order to complete a dialog between a user and an automated restaurant-reservation system. Our results show that the technique proposed in this paper achieves high accuracy regarding selection of the correct candidate utterance, and outperforms other state-of-the-art approaches based on neural networks.
Tasks	Dialog Learning, Goal-Oriented Dialog, Language Modelling
Published	2018-12-26
URL	http://arxiv.org/abs/1812.10356v1
PDF	http://arxiv.org/pdf/1812.10356v1.pdf
PWC	https://paperswithcode.com/paper/quantized-dialog-language-model-for-goal
Repo
Framework

Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages


Title	Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages
Authors	Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman, Vimal Manohar, Jan Trmal, Zhongqiang Huang, Najim Dehak, Sanjeev Khudanpur
Abstract	Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural to consider when no transcribed speech is available to train an ASR system in a language, adapting universal phone models using very small amounts (minutes rather than hours) of transcribed speech also needs to be studied, particularly with state-of-the-art DNN-based acoustic models. The DARPA LORELEI program provides a framework for such very-low-resource ASR studies, and provides an extrinsic metric for evaluating ASR performance in a humanitarian assistance, disaster relief setting. This paper presents our Kaldi-based systems for the program, which employ a universal phone modeling approach to ASR, and describes recipes for very rapid adaptation of this universal ASR system. The results we obtain significantly outperform results obtained by many competing approaches on the NIST LoReHLT 2017 Evaluation datasets.
Tasks	Speech Recognition
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08731v2
PDF	http://arxiv.org/pdf/1802.08731v2.pdf
PWC	https://paperswithcode.com/paper/automatic-speech-recognition-and-topic
Repo
Framework