October 21, 2019

2928 words 14 mins read

Paper Group AWR 3

Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images. Stock Price Correlation Coefficient Prediction with ARIMA-LSTM Hybrid Model. Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification. Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation. LSCP: Locally S …

Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images


Title	Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
Authors	Gongning Luo, Suyu Dong, Kuanquan Wang, Wangmeng Zuo, Shaodong Cao, Henggui Zhang
Abstract	Left ventricular (LV) volumes estimation is a critical procedure for cardiac disease diagnosis. The objective of this paper is to address direct LV volumes prediction task. Methods: In this paper, we propose a direct volumes prediction method based on the end-to-end deep convolutional neural networks (CNN). We study the end-to-end LV volumes prediction method in items of the data preprocessing, networks structure, and multi-views fusion strategy. The main contributions of this paper are the following aspects. First, we propose a new data preprocessing method on cardiac magnetic resonance (CMR). Second, we propose a new networks structure for end-to-end LV volumes estimation. Third, we explore the representational capacity of different slices, and propose a fusion strategy to improve the prediction accuracy. Results: The evaluation results show that the proposed method outperforms other state-of-the-art LV volumes estimation methods on the open accessible benchmark datasets. The clinical indexes derived from the predicted volumes agree well with the ground truth (EDV: R2=0.974, RMSE=9.6ml; ESV: R2=0.976, RMSE=7.1ml; EF: R2=0.828, RMSE =4.71%). Conclusion: Experimental results prove that the proposed method may be useful for LV volumes prediction task. Significance: The proposed method not only has application potential for cardiac diseases screening for large-scale CMR data, but also can be extended to other medical image research fields
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03008v1
PDF	http://arxiv.org/pdf/1804.03008v1.pdf
PWC	https://paperswithcode.com/paper/multi-views-fusion-cnn-for-left-ventricular
Repo	https://github.com/luogongning/Multi-views-fusion
Framework	none

Stock Price Correlation Coefficient Prediction with ARIMA-LSTM Hybrid Model


Title	Stock Price Correlation Coefficient Prediction with ARIMA-LSTM Hybrid Model
Authors	Hyeong Kyu Choi
Abstract	Predicting the price correlation of two assets for future time periods is important in portfolio optimization. We apply LSTM recurrent neural networks (RNN) in predicting the stock price correlation coefficient of two individual stocks. RNNs are competent in understanding temporal dependencies. The use of LSTM cells further enhances its long term predictive properties. To encompass both linearity and nonlinearity in the model, we adopt the ARIMA model as well. The ARIMA model filters linear tendencies in the data and passes on the residual value to the LSTM model. The ARIMA LSTM hybrid model is tested against other traditional predictive financial models such as the full historical model, constant correlation model, single index model and the multi group model. In our empirical study, the predictive ability of the ARIMA-LSTM model turned out superior to all other financial models by a significant scale. Our work implies that it is worth considering the ARIMA LSTM model to forecast correlation coefficient for portfolio optimization.
Tasks	Portfolio Optimization, Stock Market Prediction
Published	2018-08-05
URL	http://arxiv.org/abs/1808.01560v5
PDF	http://arxiv.org/pdf/1808.01560v5.pdf
PWC	https://paperswithcode.com/paper/stock-price-correlation-coefficient
Repo	https://github.com/imhgchoi/Corr_Prediction_ARIMA_LSTM_Hybrid
Framework	none

Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification


Title	Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Authors	Long Chen, Haizhou Ai, Zijie Zhuang, Chong Shang
Abstract	Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks can handle noisy detection caused by occlusion. In order to apply optimal selection from a considerable amount of candidates in real-time, we present a novel scoring function based on a fully convolutional neural network, that shares most computations on the entire image. Moreover, we adopt a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of our tracker. Extensive experiments show that our tracker achieves real-time and state-of-the-art performance on a widely used people tracking benchmark.
Tasks	Large-Scale Person Re-Identification, Multi-Object Tracking, Multiple People Tracking, Object Tracking, Online Multi-Object Tracking, Person Re-Identification
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04427v1
PDF	http://arxiv.org/pdf/1809.04427v1.pdf
PWC	https://paperswithcode.com/paper/real-time-multiple-people-tracking-with
Repo	https://github.com/youngbin-ro/Homography-based-MOTDT
Framework	none

Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation


Title	Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
Authors	Sohil Shah, Pallabi Ghosh, Larry S Davis, Tom Goldstein
Abstract	Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for semantic segmentation and object detection tasks, a network must provide higher-resolution pixel-level outputs. To globalize information while preserving resolution, many researchers propose the inclusion of sophisticated auxiliary blocks, but these come at the cost of a considerable increase in network size and computational cost. This paper proposes stacked u-nets (SUNets), which iteratively combine features from different resolution scales while maintaining resolution. SUNets leverage the information globalization power of u-nets in a deeper network architectures that is capable of handling the complexity of natural images. SUNets perform extremely well on semantic segmentation tasks using a small number of parameters.
Tasks	Object Detection, Semantic Segmentation
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10343v1
PDF	http://arxiv.org/pdf/1804.10343v1.pdf
PWC	https://paperswithcode.com/paper/stacked-u-nets-a-no-frills-approach-to
Repo	https://github.com/shahsohil/sunets
Framework	pytorch

LSCP: Locally Selective Combination in Parallel Outlier Ensembles


Title	LSCP: Locally Selective Combination in Parallel Outlier Ensembles
Authors	Yue Zhao, Zain Nasrullah, Maciej K. Hryniewicki, Zheng Li
Abstract	In unsupervised outlier ensembles, the absence of ground truth makes the combination of base outlier detectors a challenging task. Specifically, existing parallel outlier ensembles lack a reliable way of selecting competent base detectors, affecting accuracy and stability, during model combination. In this paper, we propose a framework—called Locally Selective Combination in Parallel Outlier Ensembles (LSCP)—which addresses the issue by defining a local region around a test instance using the consensus of its nearest neighbors in randomly selected feature subspaces. The top-performing base detectors in this local region are selected and combined as the model’s final output. Four variants of the LSCP framework are compared with seven widely used parallel frameworks. Experimental results demonstrate that one of these variants, LSCP_AOM, consistently outperforms baselines on the majority of twenty real-world datasets.
Tasks	Anomaly Detection, Outlier Detection, outlier ensembles
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01528v2
PDF	http://arxiv.org/pdf/1812.01528v2.pdf
PWC	https://paperswithcode.com/paper/lscp-locally-selective-combination-in
Repo	https://github.com/yzhao062/LSCP
Framework	none

Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach


Title	Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach
Authors	Arthur Colombini Gusmão, Alvaro Henrique Chaim Correia, Glauber De Bona, Fabio Gagliardi Cozman
Abstract	Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt “pedagogical approaches” (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.
Tasks	Knowledge Base Completion
Published	2018-06-20
URL	http://arxiv.org/abs/1806.09504v1
PDF	http://arxiv.org/pdf/1806.09504v1.pdf
PWC	https://paperswithcode.com/paper/interpreting-embedding-models-of-knowledge
Repo	https://github.com/arthurcgusmao/XKE
Framework	none

Generating Wikipedia by Summarizing Long Sequences


Title	Generating Wikipedia by Summarizing Long Sequences
Authors	Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer
Abstract	We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents. We use extractive summarization to coarsely identify salient information and a neural abstractive model to generate the article. For the abstractive model, we introduce a decoder-only architecture that can scalably attend to very long sequences, much longer than typical encoder- decoder architectures used in sequence transduction. We show that this model can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. When given reference documents, we show it can extract relevant factual information as reflected in perplexity, ROUGE scores and human evaluations.
Tasks	Document Summarization, Multi-Document Summarization
Published	2018-01-30
URL	http://arxiv.org/abs/1801.10198v1
PDF	http://arxiv.org/pdf/1801.10198v1.pdf
PWC	https://paperswithcode.com/paper/generating-wikipedia-by-summarizing-long
Repo	https://github.com/tensorflow/tensor2tensor
Framework	tf

On the Art and Science of Machine Learning Explanations


Title	On the Art and Science of Machine Learning Explanations
Authors	Patrick Hall
Abstract	This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are rigorously derived and backed by long-standing theory. The methods, decision tree surrogate models, individual conditional expectation (ICE) plots, local interpretable model-agnostic explanations (LIME), partial dependence plots, and Shapley explanations, vary in terms of scope, fidelity, and suitable application domain. Along with descriptions of these methods, this text presents real-world usage recommendations supported by a use case and public, in-depth software examples for reproducibility.
Tasks
Published	2018-10-05
URL	https://arxiv.org/abs/1810.02909v3
PDF	https://arxiv.org/pdf/1810.02909v3.pdf
PWC	https://paperswithcode.com/paper/on-the-art-and-science-of-machine-learning
Repo	https://github.com/jphall663/jsm_2018_paper
Framework	none

A Human-Grounded Evaluation Benchmark for Local Explanations of Machine Learning


Title	A Human-Grounded Evaluation Benchmark for Local Explanations of Machine Learning
Authors	Sina Mohseni, Eric D. Ragan
Abstract	In order for people to be able to trust and take advantage of the results of advanced machine learning and artificial intelligence solutions for real decision making, people need to be able to understand the machine rationale for given output. Research in explain artificial intelligence (XAI) addresses the aim, but there is a need for evaluation of human relevance and understandability of explanations. Our work contributes a novel methodology for evaluating the quality or human interpretability of explanations for machine learning models. We present an evaluation benchmark for instance explanations from text and image classifiers. The explanation meta-data in this benchmark is generated from user annotations of image and text samples. We describe the benchmark and demonstrate its utility by a quantitative evaluation on explanations generated from a recent machine learning algorithm. This research demonstrates how human-grounded evaluation could be used as a measure to qualify local machine-learning explanations.
Tasks	Decision Making
Published	2018-01-16
URL	http://arxiv.org/abs/1801.05075v1
PDF	http://arxiv.org/pdf/1801.05075v1.pdf
PWC	https://paperswithcode.com/paper/a-human-grounded-evaluation-benchmark-for
Repo	https://github.com/SinaMohseni/ML-Interpretability-Evaluation-Benchmark
Framework	none

Deep Exemplar-based Colorization


Title	Deep Exemplar-based Colorization
Authors	Mingming He, Dongdong Chen, Jing Liao, Pedro V. Sander, Lu Yuan
Abstract	We propose the first deep learning approach for exemplar-based local colorization. Given a reference color image, our convolutional neural network directly maps a grayscale image to an output colorized image. Rather than using hand-crafted rules as in traditional exemplar-based methods, our end-to-end colorization network learns how to select, propagate, and predict colors from the large-scale data. The approach performs robustly and generalizes well even when using reference images that are unrelated to the input grayscale image. More importantly, as opposed to other learning-based colorization methods, our network allows the user to achieve customizable results by simply feeding different references. In order to further reduce manual effort in selecting the references, the system automatically recommends references with our proposed image retrieval algorithm, which considers both semantic and luminance information. The colorization can be performed fully automatically by simply picking the top reference suggestion. Our approach is validated through a user study and favorable quantitative comparisons to the-state-of-the-art methods. Furthermore, our approach can be naturally extended to video colorization. Our code and models will be freely available for public use.
Tasks	Colorization, Image Retrieval
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06587v2
PDF	http://arxiv.org/pdf/1807.06587v2.pdf
PWC	https://paperswithcode.com/paper/deep-exemplar-based-colorization
Repo	https://github.com/msracver/Deep-Exemplar-based-Colorization
Framework	pytorch

Mainumby: un Ayudante para la Traducción Castellano-Guaraní


Title	Mainumby: un Ayudante para la Traducción Castellano-Guaraní
Authors	Michael Gasser
Abstract	A wide range of applications play an important role in the daily work of the modern human translator. However, the computational tools designed to aid in the process of translation only benefit translation from or to a small minority of the 7,000 languages of the world, those that we may call “privileged languages”. As for those translators who work with the remaining languages, the marginalized languages in the digital world, they cannot benefit from the tools that are speeding up the production of translation in the privileged languages. We may ask whether it is possible to bridge the gap between what is available for these languages and for the marginalized ones. This paper proposes a framework for computer-assisted translation into marginalized languages and its implementation in a web application for Spanish-Guarani translation. The proposed system is based on a new theory for phrase-level translation in contexts where adequate bilingual corpora are not available: Translation by Generalized Segments (referred to as Minimal Dependency Translation in previous work).
Tasks
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08603v1
PDF	http://arxiv.org/pdf/1810.08603v1.pdf
PWC	https://paperswithcode.com/paper/mainumby-un-ayudante-para-la-traduccion
Repo	https://github.com/pywirrarika/naki
Framework	none

Prior-preconditioned conjugate gradient method for accelerated Gibbs sampling in “large $n$ & large $p$” sparse Bayesian regression


Title	Prior-preconditioned conjugate gradient method for accelerated Gibbs sampling in “large $n$ & large $p$” sparse Bayesian regression
Authors	Akihiko Nishimura, Marc A. Suchard
Abstract	In a modern observational study based on healthcare databases, the number of observations and of predictors typically range in the order of $10^5$ ~ $10^6$ and of $10^4$ ~ $10^5$. Despite the large sample size, data rarely provide sufficient information to reliably estimate such a large number of parameters. Sparse regression techniques provide potential solutions, one notable approach being the Bayesian methods based on shrinkage priors. In the “large $n$ & large $p$” setting, however, posterior computation encounters a major bottleneck at repeated sampling from a high-dimensional Gaussian distribution, whose precision matrix $\Phi$ is expensive to compute and factorize. In this article, we present a novel algorithm to speed up this bottleneck based on the following observation: we can cheaply generate a random vector $b$ such that the solution to the linear system $\Phi \beta = b$ has the desired Gaussian distribution. We can then solve the linear system by the conjugate gradient (CG) algorithm through matrix-vector multiplications by $\Phi$, without ever explicitly inverting $\Phi$. Rapid convergence of CG in this specific context is achieved by the theory of prior-preconditioning we develop. We apply our algorithm to a clinically relevant large-scale observational study with $n$ = 72,489 patients and $p$ = 22,175 clinical covariates, designed to assess the relative risk of adverse events from two alternative blood anti-coagulants. Our algorithm demonstrates an order of magnitude speed-up in the posterior computation.
Tasks
Published	2018-10-29
URL	https://arxiv.org/abs/1810.12437v4
PDF	https://arxiv.org/pdf/1810.12437v4.pdf
PWC	https://paperswithcode.com/paper/prior-preconditioned-conjugate-gradient
Repo	https://github.com/aki-nishimura/bayes-bridge
Framework	none

CU-Net: Coupled U-Nets


Title	CU-Net: Coupled U-Nets
Authors	Zhiqiang Tang, Xi Peng, Shijie Geng, Yizhe Zhu, Dimitris N. Metaxas
Abstract	We design a new connectivity pattern for the U-Net architecture. Given several stacked U-Nets, we couple each U-Net pair through the connections of their semantic blocks, resulting in the coupled U-Nets (CU-Net). The coupling connections could make the information flow more efficiently across U-Nets. The feature reuse across U-Nets makes each U-Net very parameter efficient. We evaluate the coupled U-Nets on two benchmark datasets of human pose estimation. Both the accuracy and model parameter number are compared. The CU-Net obtains comparable accuracy as state-of-the-art methods. However, it only has at least 60% fewer parameters than other approaches.
Tasks	Pose Estimation
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06521v1
PDF	http://arxiv.org/pdf/1808.06521v1.pdf
PWC	https://paperswithcode.com/paper/cu-net-coupled-u-nets
Repo	https://github.com/zhiqiangdon/CU-Net
Framework	pytorch


Title	On Evaluation of Embodied Navigation Agents
Authors	Peter Anderson, Angel Chang, Devendra Singh Chaplot, Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, Amir R. Zamir
Abstract	Skillful mobile operation in three-dimensional environments is a primary topic of study in Artificial Intelligence. The past two years have seen a surge of creative work on navigation. This creative output has produced a plethora of sometimes incompatible task definitions and evaluation protocols. To coordinate ongoing and future research in this area, we have convened a working group to study empirical methodology in navigation research. The present document summarizes the consensus recommendations of this working group. We discuss different problem statements and the role of generalization, present evaluation measures, and provide standard scenarios that can be used for benchmarking.
Tasks
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06757v1
PDF	http://arxiv.org/pdf/1807.06757v1.pdf
PWC	https://paperswithcode.com/paper/on-evaluation-of-embodied-navigation-agents
Repo	https://github.com/StanfordVL/GibsonSim2RealCallenge
Framework	tf

Deep Single-View 3D Object Reconstruction with Visual Hull Embedding


Title	Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
Authors	Hanqing Wang, Jiaolong Yang, Wei Liang, Xin Tong
Abstract	3D object reconstruction is a fundamental task of many robotics and AI problems. With the aid of deep convolutional neural networks (CNNs), 3D object reconstruction has witnessed a significant progress in recent years. However, possibly due to the prohibitively high dimension of the 3D object space, the results from deep CNNs are often prone to missing some shape details. In this paper, we present an approach which aims to preserve more shape details and improve the reconstruction quality. The key idea of our method is to leverage object mask and pose estimation from CNNs to assist the 3D shape learning by constructing a probabilistic single-view visual hull inside of the network. Our method works by first predicting a coarse shape as well as the object pose and silhouette using CNNs, followed by a novel 3D refinement CNN which refines the coarse shapes using the constructed probabilistic visual hulls. Experiment on both synthetic data and real images show that embedding a single-view visual hull for shape refinement can significantly improve the reconstruction quality by recovering more shapes details and improving shape consistency with the input image.
Tasks	3D Object Reconstruction, Object Reconstruction, Pose Estimation
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03451v1
PDF	http://arxiv.org/pdf/1809.03451v1.pdf
PWC	https://paperswithcode.com/paper/deep-single-view-3d-object-reconstruction
Repo	https://github.com/qweas120/PSVH-3d-reconstruction
Framework	tf