October 18, 2019

3276 words 16 mins read

Paper Group ANR 453

On the Evaluation and Validation of Off-the-shelf Statistical Shape Modeling Tools: A Clinical Application. Stack-U-Net: Refinement Network for Image Segmentation on the Example of Optic Disc and Cup. Distributed Readability Analysis Of Turkish Elementary School Textbooks. Amortized Context Vector Inference for Sequence-to-Sequence Networks. Experi …

On the Evaluation and Validation of Off-the-shelf Statistical Shape Modeling Tools: A Clinical Application


Title	On the Evaluation and Validation of Off-the-shelf Statistical Shape Modeling Tools: A Clinical Application
Authors	Anupama Goparaju, Ibolya Csecs, Alan Morris, Evgueni Kholmovski, Nassir Marrouche, Ross Whitaker, Shireen Elhabian
Abstract	Statistical shape modeling (SSM) has proven useful in many areas of biology and medicine as a new generation of morphometric approaches for the quantitative analysis of anatomical shapes. Recently, the increased availability of high-resolution in vivo images of anatomy has led to the development and distribution of open-source computational tools to model anatomical shapes and their variability within populations with unprecedented detail and statistical power. Nonetheless, there is little work on the evaluation and validation of such tools as related to clinical applications that rely on morphometric quantifications for treatment planning. To address this lack of validation, we systematically assess the outcome of widely used off-the-shelf SSM tools, namely ShapeWorks, SPHARM-PDM, and Deformetrica, in the context of designing closure devices for left atrium appendage (LAA) in atrial fibrillation (AF) patients to prevent stroke, where an incomplete LAA closure may be worse than no closure. This study is motivated by the potential role of SSM in the geometric design of closure devices, which could be informed by population-level statistics, and patient-specific device selection, which is driven by anatomical measurements that could be automated by relating patient-level anatomy to population-level morphometrics. Hence, understanding the consequences of different SSM tools for the final analysis is critical for the careful choice of the tool to be deployed in real clinical scenarios. Results demonstrate that estimated measurements from ShapeWorks model are more consistent compared to models from Deformetrica and SPHARM-PDM. Furthermore, ShapeWorks and Deformetrica shape models capture clinically relevant population-level variability compared to SPHARM-PDM models.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.03987v1
PDF	http://arxiv.org/pdf/1810.03987v1.pdf
PWC	https://paperswithcode.com/paper/on-the-evaluation-and-validation-of-off-the
Repo
Framework


Title	Stack-U-Net: Refinement Network for Image Segmentation on the Example of Optic Disc and Cup
Authors	Artem Sevastopolsky, Stepan Drapak, Konstantin Kiselev, Blake M. Snyder, Jeremy D. Keenan, Anastasia Georgievskaya
Abstract	In this work, we propose a special cascade network for image segmentation, which is based on the U-Net networks as building blocks and the idea of the iterative refinement. The model was mainly applied to achieve higher recognition quality for the task of finding borders of the optic disc and cup, which are relevant to the presence of glaucoma. Compared to a single U-Net and the state-of-the-art methods for the investigated tasks, very high segmentation quality has been achieved without a need for increasing the volume of datasets. Our experiments include comparison with the best-known methods on publicly available databases DRIONS-DB, RIM-ONE v.3, DRISHTI-GS, and evaluation on a private data set collected in collaboration with University of California San Francisco Medical School. The analysis of the architecture details is presented, and it is argued that the model can be employed for a broad scope of image segmentation problems of similar nature.
Tasks	Semantic Segmentation
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11294v2
PDF	http://arxiv.org/pdf/1804.11294v2.pdf
PWC	https://paperswithcode.com/paper/stack-u-net-refinement-network-for-image
Repo
Framework

Distributed Readability Analysis Of Turkish Elementary School Textbooks


Title	Distributed Readability Analysis Of Turkish Elementary School Textbooks
Authors	Betul Karakus, Ibrahim Riza Hallac, Galip Aydin
Abstract	The readability assessment deals with estimating the level of difficulty in reading texts.Many readability tests, which do not indicate execution efficiency, have been applied on specific texts to measure the reading grade level in science textbooks. In this paper, we analyze the content covered in elementary school Turkish textbooks by employing a distributed parallel processing framework based on popular MapReduce paradigm. We outline the architecture of a distributed Big Data processing system which uses Hadoop for full-text readability analysis. The readability scores of the textbooks and system performance measurements are also given in the paper.
Tasks
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03821v1
PDF	http://arxiv.org/pdf/1802.03821v1.pdf
PWC	https://paperswithcode.com/paper/distributed-readability-analysis-of-turkish
Repo
Framework

Amortized Context Vector Inference for Sequence-to-Sequence Networks


Title	Amortized Context Vector Inference for Sequence-to-Sequence Networks
Authors	Kyriacos Tolias, Ioannis Kourouklides, Sotirios Chatzis
Abstract	Neural attention (NA) has become a key component of sequence-to-sequence models that yield state-of-the-art performance in as hard tasks as abstractive document summarization (ADS) and video captioning (VC). NA mechanisms perform inference of context vectors; these constitute weighted sums of deterministic input sequence encodings, adaptively sourced over long temporal horizons. Inspired from recent work in the field of amortized variational inference (AVI), in this work we consider treating the context vectors generated by soft-attention (SA) models as latent variables, with approximate finite mixture model posteriors inferred via AVI. We posit that this formulation may yield stronger generalization capacity, in line with the outcomes of existing applications of AVI to deep networks. To illustrate our method, we implement it and experimentally evaluate it considering challenging ADS, VC, and MT benchmarks. This way, we exhibit its improved effectiveness over state-of-the-art alternatives.
Tasks	Document Summarization, Video Captioning
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09039v9
PDF	http://arxiv.org/pdf/1805.09039v9.pdf
PWC	https://paperswithcode.com/paper/amortized-context-vector-inference-for
Repo
Framework

Experience-driven Networking: A Deep Reinforcement Learning based Approach


Title	Experience-driven Networking: A Deep Reinforcement Learning based Approach
Authors	Zhiyuan Xu, Jian Tang, Jingsong Meng, Weiyi Zhang, Yanzhi Wang, Chi Harold Liu, Dejun Yang
Abstract	Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this paper, we develop a novel experience-driven approach that can learn to well control a communication network from its own experience rather than an accurate mathematical model, just as a human learns a new skill (such as driving, swimming, etc). Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in communication networks; and present a novel and highly effective DRL-based control framework, DRL-TE, for a fundamental networking problem: Traffic Engineering (TE). The proposed framework maximizes a widely-used utility function by jointly learning network environment and its dynamics, and making decisions under the guidance of powerful Deep Neural Networks (DNNs). We propose two new techniques, TE-aware exploration and actor-critic-based prioritized experience replay, to optimize the general DRL framework particularly for TE. To validate and evaluate the proposed framework, we implemented it in ns-3, and tested it comprehensively with both representative and randomly generated network topologies. Extensive packet-level simulation results show that 1) compared to several widely-used baseline methods, DRL-TE significantly reduces end-to-end delay and consistently improves the network utility, while offering better or comparable throughput; 2) DRL-TE is robust to network changes; and 3) DRL-TE consistently outperforms a state-ofthe-art DRL method (for continuous control), Deep Deterministic Policy Gradient (DDPG), which, however, does not offer satisfying performance.
Tasks	Continuous Control
Published	2018-01-17
URL	http://arxiv.org/abs/1801.05757v1
PDF	http://arxiv.org/pdf/1801.05757v1.pdf
PWC	https://paperswithcode.com/paper/experience-driven-networking-a-deep
Repo
Framework

Defect Detection from UAV Images based on Region-Based CNNs


Title	Defect Detection from UAV Images based on Region-Based CNNs
Authors	Meng Lan, Yipeng Zhang, Lefei Zhang, Bo Du
Abstract	With the wide applications of Unmanned Aerial Vehicle (UAV) in engineering such as the inspection of the electrical equipment from distance, the demands of efficient object detection algorithms for abundant images acquired by UAV have also been significantly increased in recent years. In this work, we study the performance of the region-based CNN for the electrical equipment defect detection by using the UAV images. In order to train the detection model, we collect a UAV images dataset composes of four classes of electrical equipment defects with thousands of annotated labels. Then, based on the region-based faster R-CNN model, we present a multi-class defects detection model for electrical equipment which is more efficient and accurate than traditional single class detection methods. Technically, we have replaced the RoI pooling layer with a similar operation in Tensorflow and promoted the mini-batch to 128 per image in the training procedure. These improvements have slightly increased the speed of detection without any accuracy loss. Therefore, the modified region-based CNN could simultaneously detect multi-class of defects of the electrical devices in nearly real time. Experimental results on the real word electrical equipment images demonstrate that the proposed method achieves better performance than the traditional object detection algorithms in defect detection.
Tasks	Object Detection
Published	2018-11-23
URL	http://arxiv.org/abs/1811.09473v1
PDF	http://arxiv.org/pdf/1811.09473v1.pdf
PWC	https://paperswithcode.com/paper/defect-detection-from-uav-images-based-on
Repo
Framework


Title	Data Augmentation for Brain-Computer Interfaces: Analysis on Event-Related Potentials Data
Authors	Mario Michael Krell, Anett Seeland, Su Kyoung Kim
Abstract	On image data, data augmentation is becoming less relevant due to the large amount of available training data and regularization techniques. Common approaches are moving windows (cropping), scaling, affine distortions, random noise, and elastic deformations. For electroencephalographic data, the lack of sufficient training data is still a major issue. We suggest and evaluate different approaches to generate augmented data using temporal and spatial/rotational distortions. Our results on the perception of rare stimuli (P300 data) and movement prediction (MRCP data) show that these approaches are feasible and can significantly increase the performance of signal processing chains for brain-computer interfaces by 1% to 6%.
Tasks	Data Augmentation
Published	2018-01-09
URL	http://arxiv.org/abs/1801.02730v1
PDF	http://arxiv.org/pdf/1801.02730v1.pdf
PWC	https://paperswithcode.com/paper/data-augmentation-for-brain-computer
Repo
Framework

Anomaly detection in static networks using egonets


Title	Anomaly detection in static networks using egonets
Authors	Srijan Sengupta
Abstract	Network data has rapidly emerged as an important and active area of statistical methodology. In this paper we consider the problem of anomaly detection in networks. Given a large background network, we seek to detect whether there is a small anomalous subgraph present in the network, and if such a subgraph is present, which nodes constitute the subgraph. We propose an inferential tool based on egonets to answer this question. The proposed method is computationally efficient and naturally amenable to parallel computing, and easily extends to a wide variety of network models. We demonstrate through simulation studies that the egonet method works well under a wide variety of network models. We obtain some fascinating empirical results by applying the egonet method on several well-studied benchmark datasets.
Tasks	Anomaly Detection
Published	2018-07-24
URL	http://arxiv.org/abs/1807.08925v2
PDF	http://arxiv.org/pdf/1807.08925v2.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-in-static-networks-using
Repo
Framework

Classification with imperfect training labels


Title	Classification with imperfect training labels
Authors	Timothy I. Cannings, Yingying Fan, Richard J. Samworth
Abstract	We study the effect of imperfect training data labels on the performance of classification methods. In a general setting, where the probability that an observation in the training dataset is mislabelled may depend on both the feature vector and the true label, we bound the excess risk of an arbitrary classifier trained with imperfect labels in terms of its excess risk for predicting a noisy label. This reveals conditions under which a classifier trained with imperfect labels remains consistent for classifying uncorrupted test data points. Furthermore, under stronger conditions, we derive detailed asymptotic properties for the popular $k$-nearest neighbour ($k$nn), support vector machine (SVM) and linear discriminant analysis (LDA) classifiers. One consequence of these results is that the knn and SVM classifiers are robust to imperfect training labels, in the sense that the rate of convergence of the excess risks of these classifiers remains unchanged; in fact, our theoretical and empirical results even show that in some cases, imperfect labels may improve the performance of these methods. On the other hand, the LDA classifier is shown to be typically inconsistent in the presence of label noise unless the prior probabilities of each class are equal. Our theoretical results are supported by a simulation study.
Tasks
Published	2018-05-29
URL	https://arxiv.org/abs/1805.11505v3
PDF	https://arxiv.org/pdf/1805.11505v3.pdf
PWC	https://paperswithcode.com/paper/classification-with-imperfect-training-labels
Repo
Framework

Discovery and usage of joint attention in images


Title	Discovery and usage of joint attention in images
Authors	Daniel Harari, Joshua B. Tenenbaum, Shimon Ullman
Abstract	Joint visual attention is characterized by two or more individuals looking at a common target at the same time. The ability to identify joint attention in scenes, the people involved, and their common target, is fundamental to the understanding of social interactions, including others’ intentions and goals. In this work we deal with the extraction of joint attention events, and the use of such events for image descriptions. The work makes two novel contributions. First, our extraction algorithm is the first which identifies joint visual attention in single static images. It computes 3D gaze direction, identifies the gaze target by combining gaze direction with a 3D depth map computed for the image, and identifies the common gaze target. Second, we use a human study to demonstrate the sensitivity of humans to joint attention, suggesting that the detection of such a configuration in an image can be useful for understanding the image, including the goals of the agents and their joint activity, and therefore can contribute to image captioning and related tasks.
Tasks	Image Captioning
Published	2018-04-10
URL	http://arxiv.org/abs/1804.04604v1
PDF	http://arxiv.org/pdf/1804.04604v1.pdf
PWC	https://paperswithcode.com/paper/discovery-and-usage-of-joint-attention-in
Repo
Framework

eLIAN: Enhanced Algorithm for Angle-constrained Path Finding


Title	eLIAN: Enhanced Algorithm for Angle-constrained Path Finding
Authors	Anton Andreychuk, Natalia Soboleva, Konstantin Yakovlev
Abstract	Problem of finding 2D paths of special shape, e.g. paths comprised of line segments having the property that the angle between any two consecutive segments does not exceed the predefined threshold, is considered in the paper. This problem is harder to solve than the one when shortest paths of any shape are sought, since the planer’s search space is substantially bigger as multiple search nodes corresponding to the same location need to be considered. One way to reduce the search effort is to fix the length of the path’s segment and to prune the nodes that violate the imposed constraint. This leads to incompleteness and to the sensitivity of the ‘s performance to chosen parameter value. In this work we introduce a novel technique that reduces this sensitivity by automatically adjusting the length of the path’s segment on-the-fly, e.g. during the search. Embedding this technique into the known grid-based angle-constrained path finding algorithm - LIAN, leads to notable increase of the planner’s effectiveness, e.g. success rate, while keeping efficiency, e.g. runtime, overhead at reasonable level. Experimental evaluation shows that LIAN with the suggested enhancements, dubbed eLIAN, solves up to 20% of tasks more compared to the predecessor. Meanwhile, the solution quality of eLIAN is nearly the same as the one of LIAN.
Tasks
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00797v1
PDF	http://arxiv.org/pdf/1811.00797v1.pdf
PWC	https://paperswithcode.com/paper/elian-enhanced-algorithm-for-angle
Repo
Framework

Variational Bayesian Dropout with a Hierarchical Prior


Title	Variational Bayesian Dropout with a Hierarchical Prior
Authors	Yuhang Liu, Wenyong Dong, Lei Zhang, Dong Gong, Qinfeng Shi
Abstract	Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior of network weights based on a log-uniform prior on them to learn these weights as well as dropout rate simultaneously. The log-uniform prior not only interprets the regularization capacity of Gaussian dropout in network training, but also underpins the inference of such posterior. However, the log-uniform prior is an improper prior (i.e., its integral is infinite) which causes the inference of posterior to be ill-posed, thus restricting the regularization performance of VD. To address this problem, we present a new generalization of Gaussian dropout, termed variational Bayesian dropout (VBD), which turns to exploit a hierarchical prior on the network weights and infer a new joint posterior. Specifically, we implement the hierarchical prior as a zero-mean Gaussian distribution with variance sampled from a uniform hyper-prior. Then, we incorporate such a prior into inferring the joint posterior over network weights and the variance in the hierarchical prior, with which both the network training and the dropout rate estimation can be cast into a joint optimization problem. More importantly, the hierarchical prior is a proper prior which enables the inference of posterior to be well-posed. In addition, we further show that the proposed VBD can be seamlessly applied to network compression. Experiments on both classification and network compression tasks demonstrate the superior performance of the proposed VBD in terms of regularizing network training.
Tasks
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07533v3
PDF	http://arxiv.org/pdf/1811.07533v3.pdf
PWC	https://paperswithcode.com/paper/variational-bayesian-dropout
Repo
Framework

GumBolt: Extending Gumbel trick to Boltzmann priors


Title	GumBolt: Extending Gumbel trick to Boltzmann priors
Authors	Amir H. Khoshaman, Mohammad H. Amin
Abstract	Boltzmann machines (BMs) are appealing candidates for powerful priors in variational autoencoders (VAEs), as they are capable of capturing nontrivial and multi-modal distributions over discrete variables. However, non-differentiability of the discrete units prohibits using the reparameterization trick, essential for low-noise back propagation. The Gumbel trick resolves this problem in a consistent way by relaxing the variables and distributions, but it is incompatible with BM priors. Here, we propose the GumBolt, a model that extends the Gumbel trick to BM priors in VAEs. GumBolt is significantly simpler than the recently proposed methods with BM prior and outperforms them by a considerable margin. It achieves state-of-the-art performance on permutation invariant MNIST and OMNIGLOT datasets in the scope of models with only discrete latent variables. Moreover, the performance can be further improved by allowing multi-sampled (importance-weighted) estimation of log-likelihood in training, which was not possible with previous models.
Tasks	Omniglot
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07349v2
PDF	http://arxiv.org/pdf/1805.07349v2.pdf
PWC	https://paperswithcode.com/paper/gumbolt-extending-gumbel-trick-to-boltzmann
Repo
Framework

Near Real-time Hippocampus Segmentation Using Patch-based Canonical Neural Network


Title	Near Real-time Hippocampus Segmentation Using Patch-based Canonical Neural Network
Authors	Zhongliu Xie, Duncan Gillies
Abstract	Over the past decades, state-of-the-art medical image segmentation has heavily rested on signal processing paradigms, most notably registration-based label propagation and pair-wise patch comparison, which are generally slow despite a high segmentation accuracy. In recent years, deep learning has revolutionalized computer vision with many practices outperforming prior art, in particular the convolutional neural network (CNN) studies on image classification. Deep CNN has also started being applied to medical image segmentation lately, but generally involves long training and demanding memory requirements, achieving limited success. We propose a patch-based deep learning framework based on a revisit to the classic neural network model with substantial modernization, including the use of Rectified Linear Unit (ReLU) activation, dropout layers, 2.5D tri-planar patch multi-pathway settings. In a test application to hippocampus segmentation using 100 brain MR images from the ADNI database, our approach significantly outperformed prior art in terms of both segmentation accuracy and speed: scoring a median Dice score up to 90.98% on a near real-time performance (<1s).
Tasks	Image Classification, Medical Image Segmentation, Semantic Segmentation
Published	2018-07-15
URL	http://arxiv.org/abs/1807.05482v1
PDF	http://arxiv.org/pdf/1807.05482v1.pdf
PWC	https://paperswithcode.com/paper/near-real-time-hippocampus-segmentation-using
Repo
Framework

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering


Title	Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
Authors	Medhini Narasimhan, Svetlana Lazebnik, Alexander G. Schwing
Abstract	Accurately answering a question about a given image requires combining observations with general knowledge. While this is effortless for humans, reasoning with general knowledge remains an algorithmic challenge. To advance research in this direction a novel fact-based' visual question answering (FVQA) task has been introduced recently along with a large set of curated facts which link two entities, i.e., two possible answers, via a relation. Given a question-image pair, deep network techniques have been employed to successively reduce the large set of facts until one of the two entities of the final remaining fact is predicted as the answer. We observe that a successive process which considers one fact at a time to form a local decision is sub-optimal. Instead, we develop an entity graph and use a graph convolutional network to reason’ about the correct answer by jointly considering all entities. We show on the challenging FVQA dataset that this leads to an improvement in accuracy of around 7% compared to the state of the art.
Tasks	Factual Visual Question Answering, Question Answering, Visual Question Answering
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00538v1
PDF	http://arxiv.org/pdf/1811.00538v1.pdf
PWC	https://paperswithcode.com/paper/out-of-the-box-reasoning-with-graph
Repo
Framework