January 27, 2020

2789 words 14 mins read

Paper Group ANR 1181

Rank Aggregation via Heterogeneous Thurstone Preference Models. 3D Rigid Motion Segmentation with Mixed and Unknown Number of Models. Learning to estimate label uncertainty for automatic radiology report parsing. Learning from a Teacher using Unlabeled Data. Video Stitching for Linear Camera Arrays. Information in Infinite Ensembles of Infinitely-W …

Rank Aggregation via Heterogeneous Thurstone Preference Models


Title	Rank Aggregation via Heterogeneous Thurstone Preference Models
Authors	Tao Jin, Pan Xu, Quanquan Gu, Farzad Farnoud
Abstract	We propose the Heterogeneous Thurstone Model (HTM) for aggregating ranked data, which can take the accuracy levels of different users into account. By allowing different noise distributions, the proposed HTM model maintains the generality of Thurstone’s original framework, and as such, also extends the Bradley-Terry-Luce (BTL) model for pairwise comparisons to heterogeneous populations of users. Under this framework, we also propose a rank aggregation algorithm based on alternating gradient descent to estimate the underlying item scores and accuracy levels of different users simultaneously from noisy pairwise comparisons. We theoretically prove that the proposed algorithm converges linearly up to a statistical error which matches that of the state-of-the-art method for the single-user BTL model. We evaluate the proposed HTM model and algorithm on both synthetic and real data, demonstrating that it outperforms existing methods.
Tasks
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01211v1
PDF	https://arxiv.org/pdf/1912.01211v1.pdf
PWC	https://paperswithcode.com/paper/rank-aggregation-via-heterogeneous-thurstone
Repo
Framework

3D Rigid Motion Segmentation with Mixed and Unknown Number of Models


Title	3D Rigid Motion Segmentation with Mixed and Unknown Number of Models
Authors	Xun Xu, Loong-Fah Cheong, Zhuwen Li
Abstract	Many real-world video sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation on video sequences would lead to difficulty. Even when we are confronted with a general scene-motion, the fundamental matrix approach as a model for motion segmentation still suffers from several defects, which we discuss in this paper. The full potential of the fundamental matrix approach could only be realized if we judiciously harness information from the simpler homography model. From these considerations, we propose a multi-model spectral clustering framework that synergistically combines multiple models (homography and fundamental matrix) together. We show that the performance can be substantially improved in this way. For general motion segmentation tasks, the number of independently moving objects is often unknown a priori and needs to be estimated from the observations. This is referred to as model selection and it is essentially still an open research problem. In this work, we propose a set of model selection criteria balancing data fidelity and model complexity. We perform extensive testing on existing motion segmentation datasets with both segmentation and model selection tasks, achieving state-of-the-art performance on all of them; we also put forth a more realistic and challenging dataset adapted from the KITTI benchmark, containing real-world effects such as strong perspectives and strong forward translations not seen in the traditional datasets.
Tasks	Model Selection, Motion Segmentation
Published	2019-08-16
URL	https://arxiv.org/abs/1908.06087v1
PDF	https://arxiv.org/pdf/1908.06087v1.pdf
PWC	https://paperswithcode.com/paper/3d-rigid-motion-segmentation-with-mixed-and
Repo
Framework

Learning to estimate label uncertainty for automatic radiology report parsing


Title	Learning to estimate label uncertainty for automatic radiology report parsing
Authors	Tobi Olatunji, Li Yao
Abstract	Bootstrapping labels from radiology reports has become the scalable alternative to provide inexpensive ground truth for medical imaging. Because of the domain specific nature, state-of-the-art report labeling tools are predominantly rule-based. These tools, however, typically yield a binary 0 or 1 prediction that indicates the presence or absence of abnormalities. These hard targets are then used as ground truth to train image models in the downstream, forcing models to express high degree of certainty even on cases where specificity is low. This could negatively impact the statistical efficiency of image models. We address such an issue by training a Bidirectional Long-Short Term Memory Network to augment heuristic-based discrete labels of X-ray reports from all body regions and achieve performance comparable or better than domain-specific NLP, but with additional uncertainty estimates which enable finer downstream image model training.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00673v1
PDF	https://arxiv.org/pdf/1910.00673v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-estimate-label-uncertainty-for
Repo
Framework

Learning from a Teacher using Unlabeled Data


Title	Learning from a Teacher using Unlabeled Data
Authors	Gaurav Menghani, Sujith Ravi
Abstract	Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that extend beyond the original dataset. We empirically show that a teacher model can transfer this knowledge to a student model even on an {\it out-of-distribution} dataset. Using this approach, we show promising results on MNIST, CIFAR-10, and Caltech-256 datasets using unlabeled image data from different sources. Our results are encouraging and help shed further light from the perspective of understanding knowledge distillation and utilizing unlabeled data to improve model quality.
Tasks	Model Compression
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05275v1
PDF	https://arxiv.org/pdf/1911.05275v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-a-teacher-using-unlabeled-data
Repo
Framework

Video Stitching for Linear Camera Arrays


Title	Video Stitching for Linear Camera Arrays
Authors	Wei-Sheng Lai, Orazio Gallo, Jinwei Gu, Deqing Sun, Ming-Hsuan Yang, Jan Kautz
Abstract	Despite the long history of image and video stitching research, existing academic and commercial solutions still produce strong artifacts. In this work, we propose a wide-baseline video stitching algorithm for linear camera arrays that is temporally stable and tolerant to strong parallax. Our key insight is that stitching can be cast as a problem of learning a smooth spatial interpolation between the input videos. To solve this problem, inspired by pushbroom cameras, we introduce a fast pushbroom interpolation layer and propose a novel pushbroom stitching network, which learns a dense flow field to smoothly align the multiple input videos for spatial interpolation. Our approach outperforms the state-of-the-art by a significant margin, as we show with a user study, and has immediate applications in many areas such as virtual reality, immersive telepresence, autonomous driving, and video surveillance.
Tasks	Autonomous Driving
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13622v1
PDF	https://arxiv.org/pdf/1907.13622v1.pdf
PWC	https://paperswithcode.com/paper/video-stitching-for-linear-camera-arrays
Repo
Framework

Information in Infinite Ensembles of Infinitely-Wide Neural Networks


Title	Information in Infinite Ensembles of Infinitely-Wide Neural Networks
Authors	Ravid Shwartz-Ziv, Alexander A. Alemi
Abstract	In this preliminary work, we study the generalization properties of infinite ensembles of infinitely-wide neural networks. Amazingly, this model family admits tractable calculations for many information-theoretic quantities. We report analytical and empirical investigations in the search for signals that correlate with generalization.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09189v2
PDF	https://arxiv.org/pdf/1911.09189v2.pdf
PWC	https://paperswithcode.com/paper/information-in-infinite-ensembles-of
Repo
Framework

Mobile Traffic Classification through Physical Channel Fingerprinting: a Deep Learning Approach


Title	Mobile Traffic Classification through Physical Channel Fingerprinting: a Deep Learning Approach
Authors	Hoang Duy Trinh, Angel Fernandez Gambin, Lorenza Giupponi, Michele Rossi, Paolo Dini
Abstract	The automatic classification of applications and services is an invaluable feature for new generation mobile networks. Here, we propose and validate algorithms to perform this task, at runtime, from the raw physical channel of an operative mobile network, without having to decode and/or decrypt the transmitted flows. Towards this, we decode Downlink Control Information (DCI) messages carried within the LTE Physical Downlink Control CHannel (PDCCH). DCI messages are sent by the radio cell in clear text and, in this paper, are utilized to classify the applications and services executed at the connected mobile terminals. Two datasets are collected through a large measurement campaign: one labeled, used to train the classification algorithms, and one unlabeled, collected from four radio cells in the metropolitan area of Barcelona, in Spain. Among other approaches, our Convolutional Neural Network (CNN) classifier provides the highest classification accuracy of 99%. The CNN classifier is then augmented with the capability of rejecting sessions whose patterns do not conform to those learned during the training phase, and is subsequently utilized to attain a fine grained decomposition of the traffic for the four monitored radio cells, in an online and unsupervised fashion.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11617v3
PDF	https://arxiv.org/pdf/1910.11617v3.pdf
PWC	https://paperswithcode.com/paper/classification-of-mobile-services-and-apps
Repo
Framework

Robust Motion Segmentation from Pairwise Matches


Title	Robust Motion Segmentation from Pairwise Matches
Authors	Federica Arrigoni, Tomas Pajdla
Abstract	In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only. Our contribution to this unexplored task is a novel formulation of motion segmentation as a two-step process. First, motion segmentation is performed on image pairs independently. Secondly, we combine independent pairwise segmentation results in a robust way into the final globally consistent segmentation. Our approach is inspired by the success of averaging methods. We demonstrate in simulated as well as in real experiments that our method is very effective in reducing the errors in the pairwise motion segmentation and can cope with large number of mismatches.
Tasks	Motion Segmentation
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09043v1
PDF	https://arxiv.org/pdf/1905.09043v1.pdf
PWC	https://paperswithcode.com/paper/robust-motion-segmentation-from-pairwise
Repo
Framework

Reward-Conditioned Policies


Title	Reward-Conditioned Policies
Authors	Aviral Kumar, Xue Bin Peng, Sergey Levine
Abstract	Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle, difficult to use and tune, and sensitive to seemingly innocuous implementation decisions. In contrast, imitation learning utilizes standard and well-understood supervised learning methods, but requires near-optimal expert data. Can we learn effective policies via supervised learning without demonstrations? The main idea that we explore in this work is that non-expert trajectories collected from sub-optimal policies can be viewed as optimal supervision, not for maximizing the reward, but for matching the reward of the given trajectory. By then conditioning the policy on the numerical value of the reward, we can obtain a policy that generalizes to larger returns. We show how such an approach can be derived as a principled method for policy search, discuss several variants, and compare the method experimentally to a variety of current reinforcement learning methods on standard benchmarks.
Tasks	Imitation Learning
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13465v1
PDF	https://arxiv.org/pdf/1912.13465v1.pdf
PWC	https://paperswithcode.com/paper/reward-conditioned-policies
Repo
Framework

An improved sex specific and age dependent classification model for Parkinson’s diagnosis using handwriting measurement


Title	An improved sex specific and age dependent classification model for Parkinson’s diagnosis using handwriting measurement
Authors	Ujjwal Gupta, Hritik Bansal, Deepak Joshi
Abstract	Accurate diagnosis is crucial for preventing the progression of Parkinson’s, as well as improving the quality of life with individuals with Parkinson’s disease. In this paper, we develop a sex-specific and age-dependent classification method to diagnose the Parkinson’s disease using the online handwriting recorded from individuals with Parkinson’s(n=37;m/f-19/18;age-69.3+-10.9years) and healthy controls(n=38;m/f-20/18;age-62.4+-11.3 years).The sex specific and age dependent classifier was observed significantly outperforming the generalized classifier. An improved accuracy of 83.75%(SD+1.63) with female specific classifier, and 79.55%(SD=1.58) with old age dependent classifier was observed in comparison to 75.76%(SD=1.17) accuracy with the generalized classifier. Finally, combining the age and sex information proved to be encouraging in classification. We performed a rigorous analysis to observe the dominance of sex specific and age dependent features for Parkinson’s detection and ranked them using the support vector machine(SVM) ranking method. Distinct set of features were observed to be dominating for higher classification accuracy in different category of classification.
Tasks
Published	2019-04-21
URL	https://arxiv.org/abs/1904.09651v6
PDF	https://arxiv.org/pdf/1904.09651v6.pdf
PWC	https://paperswithcode.com/paper/gender-specific-and-age-dependent
Repo
Framework

Fused Lasso for Feature Selection using Structural Information


Title	Fused Lasso for Feature Selection using Structural Information
Authors	Lu Bai, Lixin Cui, Yue Wang, Philip S. Yu, Edwin R. Hancock
Abstract	Feature selection has been proven a powerful preprocessing step for high-dimensional data analysis. However, most state-of-the-art methods tend to overlook the structural correlation information between pairwise samples, which may encapsulate useful information for refining the performance of feature selection. Moreover, they usually consider candidate feature relevancy equivalent to selected feature relevancy, and some less relevant features may be misinterpreted as salient features. To overcome these issues, we propose a new feature selection method using structural correlation between pairwise samples. Our idea is based on converting the original vectorial features into structure-based feature graph representations to incorporate structural relationship between samples, and defining a new evaluation measure to compute the joint significance of pairwise feature combinations in relation to the target feature graph. Furthermore, we formulate the corresponding feature subset selection problem into a least square regression model associated with a fused lasso regularizer to simultaneously maximize the joint relevancy and minimize the redundancy of the selected features. To effectively solve the optimization problem, an iterative algorithm is developed to identify the most discriminative features. Experiments demonstrate the effectiveness of the proposed approach.
Tasks	Feature Selection, Time Series, Time Series Analysis
Published	2019-02-26
URL	https://arxiv.org/abs/1902.09947v3
PDF	https://arxiv.org/pdf/1902.09947v3.pdf
PWC	https://paperswithcode.com/paper/fused-lasso-for-feature-selection-using
Repo
Framework

Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap


Title	Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap
Authors	Edwin Fong, Simon Lyddon, Chris Holmes
Abstract	Increasingly complex datasets pose a number of challenges for Bayesian inference. Conventional posterior sampling based on Markov chain Monte Carlo can be too computationally intensive, is serial in nature and mixes poorly between posterior modes. Further, all models are misspecified, which brings into question the validity of the conventional Bayesian update. We present a scalable Bayesian nonparametric learning routine that enables posterior sampling through the optimization of suitably randomized objective functions. A Dirichlet process prior on the unknown data distribution accounts for model misspecification, and admits an embarrassingly parallel posterior bootstrap algorithm that generates independent and exact samples from the nonparametric posterior distribution. Our method is particularly adept at sampling from multimodal posterior distributions via a random restart mechanism. We demonstrate our method on Gaussian mixture model and sparse logistic regression examples.
Tasks	Bayesian Inference
Published	2019-02-08
URL	https://arxiv.org/abs/1902.03175v2
PDF	https://arxiv.org/pdf/1902.03175v2.pdf
PWC	https://paperswithcode.com/paper/scalable-nonparametric-sampling-from
Repo
Framework

Machine Learning on sWeighted Data


Title	Machine Learning on sWeighted Data
Authors	Maxim Borisyak, Nikita Kazeev
Abstract	Data analysis in high energy physics has to deal with data samples produced from different sources. One of the most widely used ways to unfold their contributions is the sPlot technique. It uses the results of a maximum likelihood fit to assign weights to events. Some weights produced by sPlot are by design negative. Negative weights make it difficult to apply machine learning methods. The loss function becomes unbounded. This leads to divergent neural network training. In this paper we propose a mathematically rigorous way to transform the weights obtained by sPlot into class probabilities conditioned on observables, thus enabling to apply any machine learning algorithm out-of-the-box.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1912.02590v1
PDF	https://arxiv.org/pdf/1912.02590v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-on-sweighted-data
Repo
Framework

Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue


Title	Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue
Authors	Jun Quan, Deyi Xiong
Abstract	The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic approaches to data augmentation at both the word and sentence level for end-to-end task-oriented dialogue and conduct an empirical study on their impact. Experimental results on the CamRest676 and KVRET datasets demonstrate that each of the four data augmentation approaches is able to obtain a significant improvement over a strong baseline in terms of Success F1 score and that the ensemble of the four approaches achieves the state-of-the-art results in the two datasets. In-depth analyses further confirm that our methods adequately increase the diversity of user utterances, which enables the end-to-end model to learn features robustly.
Tasks	Data Augmentation, Task-Oriented Dialogue Systems
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02478v1
PDF	https://arxiv.org/pdf/1912.02478v1.pdf
PWC	https://paperswithcode.com/paper/effective-data-augmentation-approaches-to-end
Repo
Framework

Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data


Title	Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data
Authors	Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Abstract	Time series forecasting is a crucial component of many important applications, ranging from forecasting the stock markets to energy load prediction. The high-dimensionality, velocity and variety of the data collected in these applications pose significant and unique challenges that must be carefully addressed for each of them. In this work, a novel Temporal Logistic Neural Bag-of-Features approach, that can be used to tackle these challenges, is proposed. The proposed method can be effectively combined with deep neural networks, leading to powerful deep learning models for time series analysis. However, combining existing BoF formulations with deep feature extractors pose significant challenges: the distribution of the input features is not stationary, tuning the hyper-parameters of the model can be especially difficult and the normalizations involved in the BoF model can cause significant instabilities during the training process. The proposed method is capable of overcoming these limitations by a employing a novel adaptive scaling mechanism and replacing the classical Gaussian-based density estimation involved in the regular BoF model with a logistic kernel. The effectiveness of the proposed approach is demonstrated using extensive experiments on a large-scale financial time series dataset that consists of more than 4 million limit orders.
Tasks	Density Estimation, Time Series, Time Series Analysis, Time Series Forecasting
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08280v1
PDF	http://arxiv.org/pdf/1901.08280v1.pdf
PWC	https://paperswithcode.com/paper/temporal-logistic-neural-bag-of-features-for
Repo
Framework