July 29, 2019

3405 words 16 mins read

Paper Group ANR 111

Automatic Segmentation of the Left Ventricle in Cardiac CT Angiography Using Convolutional Neural Network. Contextual Explanation Networks. Why are Big Data Matrices Approximately Low Rank?. Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems. A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping. A Deep L …

Automatic Segmentation of the Left Ventricle in Cardiac CT Angiography Using Convolutional Neural Network


Title	Automatic Segmentation of the Left Ventricle in Cardiac CT Angiography Using Convolutional Neural Network
Authors	Majd Zreik, Tim Leiner, Bob D. de Vos, Robbert W. van Hamersvelt, Max A. Viergever, Ivana Isgum
Abstract	Accurate delineation of the left ventricle (LV) is an important step in evaluation of cardiac function. In this paper, we present an automatic method for segmentation of the LV in cardiac CT angiography (CCTA) scans. Segmentation is performed in two stages. First, a bounding box around the LV is detected using a combination of three convolutional neural networks (CNNs). Subsequently, to obtain the segmentation of the LV, voxel classification is performed within the defined bounding box using a CNN. The study included CCTA scans of sixty patients, fifty scans were used to train the CNNs for the LV localization, five scans were used to train LV segmentation and the remaining five scans were used for testing the method. Automatic segmentation resulted in the average Dice coefficient of 0.85 and mean absolute surface distance of 1.1 mm. The results demonstrate that automatic segmentation of the LV in CCTA scans using voxel classification with convolutional neural networks is feasible.
Tasks
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05698v1
PDF	http://arxiv.org/pdf/1704.05698v1.pdf
PWC	https://paperswithcode.com/paper/automatic-segmentation-of-the-left-ventricle
Repo
Framework

Contextual Explanation Networks


Title	Contextual Explanation Networks
Authors	Maruan Al-Shedivat, Avinava Dubey, Eric P. Xing
Abstract	Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This motivates the development of models that are equally accurate but can be also easily inspected and assessed beyond their predictive performance. To this end, we introduce contextual explanation networks (CENs)—a class of architectures that learn to predict by generating and utilizing intermediate, simplified probabilistic models. Specifically, CENs generate parameters for intermediate graphical models which are further used for prediction and play the role of explanations. Contrary to the existing post-hoc model-explanation tools, CENs learn to predict and to explain jointly. Our approach offers two major advantages: (i) for each prediction, valid, instance-specific explanations are generated with no computational overhead and (ii) prediction via explanation acts as a regularizer and boosts performance in low-resource settings. We analyze the proposed framework theoretically and experimentally. Our results on image and text classification and survival analysis tasks demonstrate that CENs are not only competitive with the state-of-the-art methods but also offer additional insights behind each prediction, that are valuable for decision support. We also show that while post-hoc methods may produce misleading explanations in certain cases, CENs are always consistent and allow to detect such cases systematically.
Tasks	Survival Analysis, Text Classification
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10301v3
PDF	http://arxiv.org/pdf/1705.10301v3.pdf
PWC	https://paperswithcode.com/paper/contextual-explanation-networks
Repo
Framework

Why are Big Data Matrices Approximately Low Rank?


Title	Why are Big Data Matrices Approximately Low Rank?
Authors	Madeleine Udell, Alex Townsend
Abstract	Matrices of (approximate) low rank are pervasive in data science, appearing in recommender systems, movie preferences, topic models, medical records, and genomics. While there is a vast literature on how to exploit low rank structure in these datasets, there is less attention on explaining why the low rank structure appears in the first place. Here, we explain the effectiveness of low rank models in data science by considering a simple generative model for these matrices: we suppose that each row or column is associated to a (possibly high dimensional) bounded latent variable, and entries of the matrix are generated by applying a piecewise analytic function to these latent variables. These matrices are in general full rank. However, we show that we can approximate every entry of an $m \times n$ matrix drawn from this model to within a fixed absolute error by a low rank matrix whose rank grows as $\mathcal O(\log(m + n))$. Hence any sufficiently large matrix from such a latent variable model can be approximated, up to a small entrywise error, by a low rank matrix.
Tasks	Recommendation Systems, Topic Models
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07474v2
PDF	http://arxiv.org/pdf/1705.07474v2.pdf
PWC	https://paperswithcode.com/paper/why-are-big-data-matrices-approximately-low
Repo
Framework

Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems


Title	Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems
Authors	Stefano V. Albrecht, Peter Stone
Abstract	Much research in artificial intelligence is concerned with the development of autonomous agents that can interact effectively with other agents. An important aspect of such agents is the ability to reason about the behaviours of other agents, by constructing models which make predictions about various properties of interest (such as actions, goals, beliefs) of the modelled agents. A variety of modelling approaches now exist which vary widely in their methodology and underlying assumptions, catering to the needs of the different sub-communities within which they were developed and reflecting the different practical uses for which they are intended. The purpose of the present article is to provide a comprehensive survey of the salient modelling methods which can be found in the literature. The article concludes with a discussion of open problems which may form the basis for fruitful future research.
Tasks
Published	2017-09-23
URL	http://arxiv.org/abs/1709.08071v2
PDF	http://arxiv.org/pdf/1709.08071v2.pdf
PWC	https://paperswithcode.com/paper/autonomous-agents-modelling-other-agents-a
Repo
Framework

A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping


Title	A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Authors	Debang Li, Huikai Wu, Junge Zhang, Kaiqi Huang
Abstract	Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box supervision) rely on the sliding window mechanism. The sliding window mechanism requires fixed aspect ratios and limits the cropping region with arbitrary size. Moreover, the sliding window method usually produces tens of thousands of windows on the input image which is very time-consuming. Motivated by these challenges, we firstly formulate the aesthetic image cropping as a sequential decision-making process and propose a weakly supervised Aesthetics Aware Reinforcement Learning (A2-RL) framework to address this problem. Particularly, the proposed method develops an aesthetics aware reward function which especially benefits image cropping. Similar to human’s decision making, we use a comprehensive state representation including both the current observation and the historical experience. We train the agent using the actor-critic architecture in an end-to-end manner. The agent is evaluated on several popular unseen cropping datasets. Experiment results show that our method achieves the state-of-the-art performance with much fewer candidate windows and much less time compared with previous weakly supervised methods.
Tasks	Decision Making, Image Cropping
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04595v3
PDF	http://arxiv.org/pdf/1709.04595v3.pdf
PWC	https://paperswithcode.com/paper/a2-rl-aesthetics-aware-reinforcement-learning
Repo
Framework

A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading


Title	A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading
Authors	Jordi de la Torre, Aida Valls, Domenec Puig
Abstract	Deep neural network models have been proven to be very successful in image classification tasks, also for medical diagnosis, but their main concern is its lack of interpretability. They use to work as intuition machines with high statistical confidence but unable to give interpretable explanations about the reported results. The vast amount of parameters of these models make difficult to infer a rationale interpretation from them. In this paper we present a diabetic retinopathy interpretable classifier able to classify retine images into the different levels of disease severity and of explaining its results by assigning a score for every point in the hidden and input space, evaluating its contribution to the final classification in a linear way. The generated visual maps can be interpreted by an expert in order to compare its own knowledge with the interpretation given by the model.
Tasks	Image Classification, Medical Diagnosis
Published	2017-12-21
URL	http://arxiv.org/abs/1712.08107v1
PDF	http://arxiv.org/pdf/1712.08107v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-interpretable-classifier-for
Repo
Framework

Provable Inductive Robust PCA via Iterative Hard Thresholding


Title	Provable Inductive Robust PCA via Iterative Hard Thresholding
Authors	U. N. Niranjan, Arun Rajkumar, Theja Tulabandhula
Abstract	The robust PCA problem, wherein, given an input data matrix that is the superposition of a low-rank matrix and a sparse matrix, we aim to separate out the low-rank and sparse components, is a well-studied problem in machine learning. One natural question that arises is that, as in the inductive setting, if features are provided as input as well, can we hope to do better? Answering this in the affirmative, the main goal of this paper is to study the robust PCA problem while incorporating feature information. In contrast to previous works in which recovery guarantees are based on the convex relaxation of the problem, we propose a simple iterative algorithm based on hard-thresholding of appropriate residuals. Under weaker assumptions than previous works, we prove the global convergence of our iterative procedure; moreover, it admits a much faster convergence rate and lesser computational complexity per iteration. In practice, through systematic synthetic and real data simulations, we confirm our theoretical findings regarding improvements obtained by using feature information.
Tasks
Published	2017-04-02
URL	http://arxiv.org/abs/1704.00367v2
PDF	http://arxiv.org/pdf/1704.00367v2.pdf
PWC	https://paperswithcode.com/paper/provable-inductive-robust-pca-via-iterative
Repo
Framework

Diversity-Promoting Bayesian Learning of Latent Variable Models


Title	Diversity-Promoting Bayesian Learning of Latent Variable Models
Authors	Pengtao Xie, Jun Zhu, Eric P. Xing
Abstract	To address three important issues involved in latent variable models (LVMs), including capturing infrequent patterns, achieving small-sized but expressive models and alleviating overfitting, several studies have been devoted to “diversifying” LVMs, which aim at encouraging the components in LVMs to be diverse. Most existing studies fall into a frequentist-style regularization framework, where the components are learned via point estimation. In this paper, we investigate how to “diversify” LVMs in the paradigm of Bayesian learning. We propose two approaches that have complementary advantages. One is to define a diversity-promoting mutual angular prior which assigns larger density to components with larger mutual angles and use this prior to affect the posterior via Bayes’ rule. We develop two efficient approximate posterior inference algorithms based on variational inference and MCMC sampling. The other approach is to impose diversity-promoting regularization directly over the post-data distribution of components. We also extend our approach to “diversify” Bayesian nonparametric models where the number of components is infinite. A sampling algorithm based on slice sampling and Hamiltonian Monte Carlo is developed. We apply these methods to “diversify” Bayesian mixture of experts model and infinite latent feature model. Experiments on various datasets demonstrate the effectiveness and efficiency of our methods.
Tasks	Latent Variable Models
Published	2017-11-23
URL	http://arxiv.org/abs/1711.08770v1
PDF	http://arxiv.org/pdf/1711.08770v1.pdf
PWC	https://paperswithcode.com/paper/diversity-promoting-bayesian-learning-of
Repo
Framework

Efficient Representative Subset Selection over Sliding Windows


Title	Efficient Representative Subset Selection over Sliding Windows
Authors	Yanhao Wang, Yuchen Li, Kian-Lee Tan
Abstract	Representative subset selection (RSS) is an important tool for users to draw insights from massive datasets. Existing literature models RSS as the submodular maximization problem to capture the “diminishing returns” property of the representativeness of selected subsets, but often only has a single constraint (e.g., cardinality), which limits its applications in many real-world problems. To capture the data recency issue and support different types of constraints, we formulate dynamic RSS in data streams as maximizing submodular functions subject to general $d$-knapsack constraints (SMDK) over sliding windows. We propose a \textsc{KnapWindow} framework (KW) for SMDK. KW utilizes the \textsc{KnapStream} algorithm (KS) for SMDK in append-only streams as a subroutine. It maintains a sequence of checkpoints and KS instances over the sliding window. Theoretically, KW is $\frac{1-\varepsilon}{1+d}$-approximate for SMDK. Furthermore, we propose a \textsc{KnapWindowPlus} framework (KW$^{+}$) to improve upon KW. KW$^{+}$ builds an index \textsc{SubKnapChk} to manage the checkpoints and KS instances. \textsc{SubKnapChk} deletes a checkpoint whenever it can be approximated by its successors. By keeping much fewer checkpoints, KW$^{+}$ achieves higher efficiency than KW while still guaranteeing a $\frac{1-\varepsilon’}{2+2d}$-approximate solution for SMDK. Finally, we evaluate the efficiency and solution quality of KW and KW$^{+}$ in real-world datasets. The experimental results demonstrate that KW achieves more than two orders of magnitude speedups over the batch baseline and preserves high-quality solutions for SMDK over sliding windows. KW$^{+}$ further runs 5-10 times faster than KW while providing solutions with equivalent or even better utilities.
Tasks
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04764v2
PDF	http://arxiv.org/pdf/1706.04764v2.pdf
PWC	https://paperswithcode.com/paper/efficient-representative-subset-selection
Repo
Framework

Extracting urban impervious surface from GF-1 imagery using one-class classifiers


Title	Extracting urban impervious surface from GF-1 imagery using one-class classifiers
Authors	Yao Yao, Jialv He, Jinbao Zhang, Yatao Zhang
Abstract	Impervious surface area is a direct consequence of the urbanization, which also plays an important role in urban planning and environmental management. With the rapidly technical development of remote sensing, monitoring urban impervious surface via high spatial resolution (HSR) images has attracted unprecedented attention recently. Traditional multi-classes models are inefficient for impervious surface extraction because it requires labeling all needed and unneeded classes that occur in the image exhaustively. Therefore, we need to find a reliable one-class model to classify one specific land cover type without labeling other classes. In this study, we investigate several one-class classifiers, such as Presence and Background Learning (PBL), Positive Unlabeled Learning (PUL), OCSVM, BSVM and MAXENT, to extract urban impervious surface area using high spatial resolution imagery of GF-1, China’s new generation of high spatial remote sensing satellite, and evaluate the classification accuracy based on artificial interpretation results. Compared to traditional multi-classes classifiers (ANN and SVM), the experimental results indicate that PBL and PUL provide higher classification accuracy, which is similar to the accuracy provided by ANN model. Meanwhile, PBL and PUL outperforms OCSVM, BSVM, MAXENT and SVM models. Hence, the one-class classifiers only need a small set of specific samples to train models without losing predictive accuracy, which is supposed to gain more attention on urban impervious surface extraction or other one specific land cover type.
Tasks
Published	2017-05-13
URL	http://arxiv.org/abs/1705.04824v1
PDF	http://arxiv.org/pdf/1705.04824v1.pdf
PWC	https://paperswithcode.com/paper/extracting-urban-impervious-surface-from-gf-1
Repo
Framework

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data


Title	SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Authors	Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz
Abstract	Neural networks exhibit good generalization behavior in the over-parameterized regime, where the number of network parameters exceeds the number of observations. Nonetheless, current generalization bounds for neural networks fail to explain this phenomenon. In an attempt to bridge this gap, we study the problem of learning a two-layer over-parameterized neural network, when the data is generated by a linearly separable function. In the case where the network has Leaky ReLU activations, we provide both optimization and generalization guarantees for over-parameterized networks. Specifically, we prove convergence rates of SGD to a global minimum and provide generalization guarantees for this global minimum that are independent of the network size. Therefore, our result clearly shows that the use of SGD for optimization both finds a global minimum, and avoids overfitting despite the high capacity of the model. This is the first theoretical demonstration that SGD can avoid overfitting, when learning over-specified neural network classifiers.
Tasks
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10174v1
PDF	http://arxiv.org/pdf/1710.10174v1.pdf
PWC	https://paperswithcode.com/paper/sgd-learns-over-parameterized-networks-that
Repo
Framework

DNN and CNN with Weighted and Multi-task Loss Functions for Audio Event Detection


Title	DNN and CNN with Weighted and Multi-task Loss Functions for Audio Event Detection
Authors	Huy Phan, Martin Krawczyk-Becker, Timo Gerkmann, Alfred Mertins
Abstract	This report presents our audio event detection system submitted for Task 2, “Detection of rare sound events”, of DCASE 2017 challenge. The proposed system is based on convolutional neural networks (CNNs) and deep neural networks (DNNs) coupled with novel weighted and multi-task loss functions and state-of-the-art phase-aware signal enhancement. The loss functions are tailored for audio event detection in audio streams. The weighted loss is designed to tackle the common issue of imbalanced data in background/foreground classification while the multi-task loss enables the networks to simultaneously model the class distribution and the temporal structures of the target events for recognition. Our proposed systems significantly outperform the challenge baseline, improving F-score from 72.7% to 90.0% and reducing detection error rate from 0.53 to 0.18 on average on the development data. On the evaluation data, our submission obtains an average F1-score of 88.3% and an error rate of 0.22 which are significantly better than those obtained by the DCASE baseline (i.e. an F1-score of 64.1% and an error rate of 0.64).
Tasks
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03211v2
PDF	http://arxiv.org/pdf/1708.03211v2.pdf
PWC	https://paperswithcode.com/paper/dnn-and-cnn-with-weighted-and-multi-task-loss
Repo
Framework

The Achievement of Higher Flexibility in Multiple Choice-based Tests Using Image Classification Techniques


Title	The Achievement of Higher Flexibility in Multiple Choice-based Tests Using Image Classification Techniques
Authors	Mahmoud Afifi, Khaled F. Hussain
Abstract	In spite of the high accuracy of the existing optical mark reading (OMR) systems and devices, a few restrictions remain existent. In this work, we aim to reduce the restrictions of multiple choice questions (MCQ) within tests. We use an image registration technique to extract the answer boxes from answer sheets. Unlike other systems that rely on simple image processing steps to recognize the extracted answer boxes, we address the problem from another perspective by training a machine learning classifier to recognize the class of each answer box (i.e., confirmed, crossed out, or blank answer). This gives us the ability to deal with a variety of shading and mark patterns, and distinguish between chosen (i.e., confirmed) and canceled answers (i.e., crossed out). All existing machine learning techniques require a large number of examples in order to train a model for classification, therefore we present a dataset including six real MCQ assessments with different answer sheet templates. We evaluate two strategies of classification: a straight-forward approach and a two-stage classifier approach. We test two handcrafted feature methods and a convolutional neural network. In the end, we present an easy-to-use graphical user interface of the proposed system. Compared with existing OMR systems, the proposed system has the least constraints and achieves a high accuracy. We believe that the presented work will further direct the development of OMR systems towards reducing the restrictions of the MCQ tests.
Tasks	Image Classification, Image Registration
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00972v9
PDF	http://arxiv.org/pdf/1711.00972v9.pdf
PWC	https://paperswithcode.com/paper/the-achievement-of-higher-flexibility-in
Repo
Framework

Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds


Title	Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds
Authors	Zhiyu Lin, Brent Harrison, Aaron Keech, Mark O. Riedl
Abstract	We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy model, or explore the agent’s environment. Managing the trade-off between these three strategies allows DRL agents to be robust to inconsistent or intermittent human feedback. Through experimentation using a synthetic oracle, we show that our technique improves the training speed and overall performance of deep reinforcement learning in navigating three-dimensional environments using Minecraft. We further show that our technique is robust to highly innacurate human feedback and can also operate when no human feedback is given.
Tasks
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03969v1
PDF	http://arxiv.org/pdf/1709.03969v1.pdf
PWC	https://paperswithcode.com/paper/explore-exploit-or-listen-combining-human
Repo
Framework

A dynamic resource allocation decision model for IT security


Title	A dynamic resource allocation decision model for IT security
Authors	Lotfi Hajjem, Salah Benabdallah, Fouad Ben Abdelaziz
Abstract	Today, with the continued growth in using information and communication technologies (ICT) for business purposes, business organizations become increasingly dependent on their information systems. Thus, they need to protect them from the different attacks exploiting their vulnerabilities. To do so, the organization has to use security technologies, which may be proactive or reactive ones. Each security technology has a relative cost and addresses specific vulnerabilities. Therefore, the organization has to put in place the appropriate security technologies set that minimizes the information system s vulnerabilities with a minimal cost. This bi objective problem will be considered as a resources allocation problem (RAP) where security technologies represent the resources to be allocated. However, the set of vulnerabilities may change, periodically, with the continual appearance of new ones. Therefore, the security technologies set should be flexible to face these changes, in real time, and the problem becomes a dynamic one. In this paper, we propose a harmony search based algorithm to solve the bi objective dynamic resource allocation decision model. This approach was compared to a genetic algorithm and provided good results.
Tasks
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06713v1
PDF	http://arxiv.org/pdf/1704.06713v1.pdf
PWC	https://paperswithcode.com/paper/a-dynamic-resource-allocation-decision-model
Repo
Framework