February 2, 2020

3266 words 16 mins read

Paper Group AWR 5

Paper Group AWR 5

Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks. CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing. DAOC: Stable Clustering of Large Networks. A Topic-Agnostic Approach for Identifying Fake News Pages. Compositio …

Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks

Title Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
Authors Georgios Kissas, Yibo Yang, Eileen Hwuang, Walter R. Witschey, John A. Detre, Paris Perdikaris
Abstract Advances in computational science offer a principled pipeline for predictive modeling of cardiovascular flows and aspire to provide a valuable tool for monitoring, diagnostics and surgical planning. Such models can be nowadays deployed on large patient-specific topologies of systemic arterial networks and return detailed predictions on flow patterns, wall shear stresses, and pulse wave propagation. However, their success heavily relies on tedious pre-processing and calibration procedures that typically induce a significant computational cost, thus hampering their clinical applicability. In this work we put forth a machine learning framework that enables the seamless synthesis of non-invasive in-vivo measurement techniques and computational flow dynamics models derived from first physical principles. We illustrate this new paradigm by showing how one-dimensional models of pulsatile flow can be used to constrain the output of deep neural networks such that their predictions satisfy the conservation of mass and momentum principles. Once trained on noisy and scattered clinical data of flow and wall displacement, these networks can return physically consistent predictions for velocity, pressure and wall displacement pulse wave propagation, all without the need to employ conventional simulators. A simple post-processing of these outputs can also provide a cheap and effective way for estimating Windkessel model parameters that are required for the calibration of traditional computational models. The effectiveness of the proposed techniques is demonstrated through a series of prototype benchmarks, as well as a realistic clinical case involving in-vivo measurements near the aorta/carotid bifurcation of a healthy human subject.
Tasks Calibration
Published 2019-05-13
URL https://arxiv.org/abs/1905.04817v2
PDF https://arxiv.org/pdf/1905.04817v2.pdf
PWC https://paperswithcode.com/paper/machine-learning-in-cardiovascular-flows
Repo https://github.com/PredictiveIntelligenceLab/1DBloodFlowPINNs
Framework none

CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing

Title CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
Authors Kevin Duarte, Yogesh S Rawat, Mubarak Shah
Abstract In this work we propose a capsule-based approach for semi-supervised video object segmentation. Current video object segmentation methods are frame-based and often require optical flow to capture temporal consistency across frames which can be difficult to compute. To this end, we propose a video based capsule network, CapsuleVOS, which can segment several frames at once conditioned on a reference frame and segmentation mask. This conditioning is performed through a novel routing algorithm for attention-based efficient capsule selection. We address two challenging issues in video object segmentation: 1) segmentation of small objects and 2) occlusion of objects across time. The issue of segmenting small objects is addressed with a zooming module which allows the network to process small spatial regions of the video. Apart from this, the framework utilizes a novel memory module based on recurrent networks which helps in tracking objects when they move out of frame or are occluded. The network is trained end-to-end and we demonstrate its effectiveness on two benchmark video object segmentation datasets; it outperforms current offline approaches on the Youtube-VOS dataset while having a run-time that is almost twice as fast as competing methods. The code is publicly available at https://github.com/KevinDuarte/CapsuleVOS.
Tasks Optical Flow Estimation, Semantic Segmentation, Semi-supervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published 2019-09-30
URL https://arxiv.org/abs/1910.00132v1
PDF https://arxiv.org/pdf/1910.00132v1.pdf
PWC https://paperswithcode.com/paper/capsulevos-semi-supervised-video-object
Repo https://github.com/KevinDuarte/CapsuleVOS
Framework tf

DAOC: Stable Clustering of Large Networks

Title DAOC: Stable Clustering of Large Networks
Authors Artem Lutov, Mourad Khayati, Philippe Cudré-Mauroux
Abstract Clustering is a crucial component of many data mining systems involving the analysis and exploration of various data. Data diversity calls for clustering algorithms to be accurate while providing stable (i.e., deterministic and robust) results on arbitrary input networks. Moreover, modern systems often operate with large datasets, which implicitly constrains the complexity of the clustering algorithm. Existing clustering techniques are only partially stable, however, as they guarantee either determinism or robustness. To address this issue, we introduce DAOC, a Deterministic and Agglomerative Overlapping Clustering algorithm. DAOC leverages a new technique called Overlap Decomposition to identify fine-grained clusters in a deterministic way capturing multiple optima. In addition, it leverages a novel consensus approach, Mutual Maximal Gain, to ensure robustness and further improve the stability of the results while still being capable of identifying micro-scale clusters. Our empirical results on both synthetic and real-world networks show that DAOC yields stable clusters while being on average 25% more accurate than state-of-the-art deterministic algorithms without requiring any tuning. Our approach has the ambition to greatly simplify and speed up data analysis tasks involving iterative processing (need for determinism) as well as data fluctuations (need for robustness) and to provide accurate and reproducible results.
Tasks
Published 2019-09-19
URL https://arxiv.org/abs/1909.08786v2
PDF https://arxiv.org/pdf/1909.08786v2.pdf
PWC https://paperswithcode.com/paper/daoc-stable-clustering-of-large-networks
Repo https://github.com/eXascaleInfolab/daoc
Framework none

A Topic-Agnostic Approach for Identifying Fake News Pages

Title A Topic-Agnostic Approach for Identifying Fake News Pages
Authors Sonia Castelo, Thais Almeida, Anas Elghafari, Aécio Santos, Kien Pham, Eduardo Nakamura, Juliana Freire
Abstract Fake news and misinformation have been increasingly used to manipulate popular opinion and influence political processes. To better understand fake news, how they are propagated, and how to counter their effect, it is necessary to first identify them. Recently, approaches have been proposed to automatically classify articles as fake based on their content. An important challenge for these approaches comes from the dynamic nature of news: as new political events are covered, topics and discourse constantly change and thus, a classifier trained using content from articles published at a given time is likely to become ineffective in the future. To address this challenge, we propose a topic-agnostic (TAG) classification strategy that uses linguistic and web-markup features to identify fake news pages. We report experimental results using multiple data sets which show that our approach attains high accuracy in the identification of fake news, even as topics evolve over time.
Tasks
Published 2019-05-02
URL https://arxiv.org/abs/1905.00957v1
PDF https://arxiv.org/pdf/1905.00957v1.pdf
PWC https://paperswithcode.com/paper/a-topic-agnostic-approach-for-identifying
Repo https://github.com/soniacq/FakeNewsClassifier
Framework none

Compositional Coding for Collaborative Filtering

Title Compositional Coding for Collaborative Filtering
Authors Chenghao Liu, Tao Lu, Xin Wang, Zhiyong Cheng, Jianling Sun, Steven C. H. Hoi
Abstract Efficiency is crucial to the online recommender systems. Representing users and items as binary vectors for Collaborative Filtering (CF) can achieve fast user-item affinity computation in the Hamming space, in recent years, we have witnessed an emerging research effort in exploiting binary hashing techniques for CF methods. However, CF with binary codes naturally suffers from low accuracy due to limited representation capability in each bit, which impedes it from modeling complex structure of the data. In this work, we attempt to improve the efficiency without hurting the model performance by utilizing both the accuracy of real-valued vectors and the efficiency of binary codes to represent users/items. In particular, we propose the Compositional Coding for Collaborative Filtering (CCCF) framework, which not only gains better recommendation efficiency than the state-of-the-art binarized CF approaches but also achieves even higher accuracy than the real-valued CF method. Specifically, CCCF innovatively represents each user/item with a set of binary vectors, which are associated with a sparse real-value weight vector. Each value of the weight vector encodes the importance of the corresponding binary vector to the user/item. The continuous weight vectors greatly enhances the representation capability of binary codes, and its sparsity guarantees the processing speed. Furthermore, an integer weight approximation scheme is proposed to further accelerate the speed. Based on the CCCF framework, we design an efficient discrete optimization algorithm to learn its parameters. Extensive experiments on three real-world datasets show that our method outperforms the state-of-the-art binarized CF methods (even achieves better performance than the real-valued CF method) by a large margin in terms of both recommendation accuracy and efficiency.
Tasks Recommendation Systems
Published 2019-05-09
URL https://arxiv.org/abs/1905.03752v1
PDF https://arxiv.org/pdf/1905.03752v1.pdf
PWC https://paperswithcode.com/paper/190503752
Repo https://github.com/3140102441/CCCF
Framework none

Prune and Replace NAS

Title Prune and Replace NAS
Authors Kevin Alexander Laube, Andreas Zell
Abstract While recent NAS algorithms are thousands of times faster than the pioneering works, it is often overlooked that they use fewer candidate operations, resulting in a significantly smaller search space. We present PR-DARTS, a NAS algorithm that discovers strong network configurations in a much larger search space and a single day. A small candidate operation pool is used, from which candidates are progressively pruned and replaced with better performing ones. Experiments on CIFAR-10 and CIFAR-100 achieve 2.51% and 15.53% test error, respectively, despite searching in a space where each cell has 150 times as many possible configurations than in the DARTS baseline. Code is available at https://github.com/cogsys-tuebingen/prdarts
Tasks
Published 2019-06-18
URL https://arxiv.org/abs/1906.07528v2
PDF https://arxiv.org/pdf/1906.07528v2.pdf
PWC https://paperswithcode.com/paper/prune-and-replace-nas
Repo https://github.com/cogsys-tuebingen/prdarts
Framework pytorch

Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection

Title Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection
Authors Anjith George, Sebastien Marcel
Abstract Face recognition has evolved as a prominent biometric authentication modality. However, vulnerability to presentation attacks curtails its reliable deployment. Automatic detection of presentation attacks is essential for secure use of face recognition technology in unattended scenarios. In this work, we introduce a Convolutional Neural Network (CNN) based framework for presentation attack detection, with deep pixel-wise supervision. The framework uses only frame level information making it suitable for deployment in smart devices with minimal computational and time overhead. We demonstrate the effectiveness of the proposed approach in public datasets for both intra as well as cross-dataset experiments. The proposed approach achieves an HTER of 0% in Replay Mobile dataset and an ACER of 0.42% in Protocol-1 of OULU dataset outperforming state of the art methods.
Tasks Face Anti-Spoofing, Face Presentation Attack Detection, Face Recognition
Published 2019-07-09
URL https://arxiv.org/abs/1907.04047v1
PDF https://arxiv.org/pdf/1907.04047v1.pdf
PWC https://paperswithcode.com/paper/deep-pixel-wise-binary-supervision-for-face
Repo https://github.com/anjith2006/bob.paper.deep_pix_bis_pad.icb2019
Framework none

Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models

Title Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models
Authors Alessandro Davide Ialongo, Mark van der Wilk, James Hensman, Carl Edward Rasmussen
Abstract We identify a new variational inference scheme for dynamical systems whose transition function is modelled by a Gaussian process. Inference in this setting has either employed computationally intensive MCMC methods, or relied on factorisations of the variational posterior. As we demonstrate in our experiments, the factorisation between latent system states and transition function can lead to a miscalibrated posterior and to learning unnecessarily large noise terms. We eliminate this factorisation by explicitly modelling the dependence between state trajectories and the Gaussian process posterior. Samples of the latent states can then be tractably generated by conditioning on this representation. The method we obtain (VCDT: variationally coupled dynamics and trajectories) gives better predictive performance and more calibrated estimates of the transition function, yet maintains the same time and space complexities as mean-field methods. Code is available at: github.com/ialong/GPt.
Tasks
Published 2019-06-13
URL https://arxiv.org/abs/1906.05828v1
PDF https://arxiv.org/pdf/1906.05828v1.pdf
PWC https://paperswithcode.com/paper/overcoming-mean-field-approximations-in
Repo https://github.com/ialong/GPt
Framework tf

StampNet: unsupervised multi-class object discovery

Title StampNet: unsupervised multi-class object discovery
Authors Joost Visser, Alessandro Corbetta, Vlado Menkovski, Federico Toschi
Abstract Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the location of the objects are not known: this adds additional degrees of freedom and increases the problem complexity. In this work, we propose StampNet, a novel autoencoding neural network that localizes shapes (objects) over a simple background in images and categorizes them simultaneously. StampNet consists of a discrete latent space that is used to categorize objects and to determine the location of the objects. The object categories are formed during the training, resulting in the discovery of a fixed set of objects. We present a set of experiments that demonstrate that StampNet is able to localize and cluster multiple overlapping shapes with varying complexity including the digits from the MNIST dataset. We also present an application of StampNet in the localization of pedestrians in overhead depth-maps.
Tasks Image Clustering
Published 2019-02-07
URL http://arxiv.org/abs/1902.02693v1
PDF http://arxiv.org/pdf/1902.02693v1.pdf
PWC https://paperswithcode.com/paper/stampnet-unsupervised-multi-class-object
Repo https://github.com/crowdflowTUe/stampnet
Framework tf

Knowledge Graph Convolutional Networks for Recommender Systems

Title Knowledge Graph Convolutional Networks for Recommender Systems
Authors Hongwei Wang, Miao Zhao, Xing Xie, Wenjie Li, Minyi Guo
Abstract To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information. In general, the attributes are not isolated but connected with each other, which forms a knowledge graph (KG). In this paper, we propose Knowledge Graph Convolutional Networks (KGCN), an end-to-end framework that captures inter-item relatedness effectively by mining their associated attributes on the KG. To automatically discover both high-order structure information and semantic information of the KG, we sample from the neighbors for each entity in the KG as their receptive field, then combine neighborhood information with bias when calculating the representation of a given entity. The receptive field can be extended to multiple hops away to model high-order proximity information and capture users’ potential long-distance interests. Moreover, we implement the proposed KGCN in a minibatch fashion, which enables our model to operate on large datasets and KGs. We apply the proposed model to three datasets about movie, book, and music recommendation, and experiment results demonstrate that our approach outperforms strong recommender baselines.
Tasks Recommendation Systems
Published 2019-03-18
URL http://arxiv.org/abs/1904.12575v1
PDF http://arxiv.org/pdf/1904.12575v1.pdf
PWC https://paperswithcode.com/paper/190412575
Repo https://github.com/hwwang55/KGCN
Framework tf

Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping

Title Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping
Authors Wushi Dong, Murat Keceli, Rafael Vescovi, Hanyu Li, Corey Adams, Elise Jennings, Samuel Flender, Tom Uram, Venkatram Vishwanath, Nicola Ferrier, Narayanan Kasthuri, Peter Littlewood
Abstract Mapping all the neurons in the brain requires automatic reconstruction of entire cells from volume electron microscopy data. The flood-filling network (FFN) architecture has demonstrated leading performance for segmenting structures from this data. However, the training of the network is computationally expensive. In order to reduce the training time, we implemented synchronous and data-parallel distributed training using the Horovod library, which is different from the asynchronous training scheme used in the published FFN code. We demonstrated that our distributed training scaled well up to 2048 Intel Knights Landing (KNL) nodes on the Theta supercomputer. Our trained models achieved similar level of inference performance, but took less training time compared to previous methods. Our study on the effects of different batch sizes on FFN training suggests ways to further improve training efficiency. Our findings on optimal learning rate and batch sizes agree with previous works.
Tasks
Published 2019-05-13
URL https://arxiv.org/abs/1905.06236v4
PDF https://arxiv.org/pdf/1905.06236v4.pdf
PWC https://paperswithcode.com/paper/scaling-distributed-training-of-flood-filling
Repo https://github.com/wushidonguc/distributed_ffn
Framework tf

Non-contact photoplethysmogram and instantaneous heart rate estimation from infrared face video

Title Non-contact photoplethysmogram and instantaneous heart rate estimation from infrared face video
Authors Natalia Martinez, Martin Bertran, Guillermo Sapiro, Hau-Tieng Wu
Abstract Extracting the instantaneous heart rate (iHR) from face videos has been well studied in recent years. It is well known that changes in skin color due to blood flow can be captured using conventional cameras. One of the main limitations of methods that rely on this principle is the need of an illumination source. Moreover, they have to be able to operate under different light conditions. One way to avoid these constraints is using infrared cameras, allowing the monitoring of iHR under low light conditions. In this work, we present a simple, principled signal extraction method that recovers the iHR from infrared face videos. We tested the procedure on 7 participants, for whom we recorded an electrocardiogram simultaneously with their infrared face video. We checked that the recovered signal matched the ground truth iHR, showing that infrared is a promising alternative to conventional video imaging for heart rate monitoring, especially in low light conditions. Code is available at https://github.com/natalialmg/IR_iHR
Tasks Heart rate estimation
Published 2019-02-14
URL http://arxiv.org/abs/1902.05194v1
PDF http://arxiv.org/pdf/1902.05194v1.pdf
PWC https://paperswithcode.com/paper/non-contact-photoplethysmogram-and
Repo https://github.com/natalialmg/IR_iHR
Framework none

Towards Best Practice in Explaining Neural Network Decisions with LRP

Title Towards Best Practice in Explaining Neural Network Decisions with LRP
Authors Maximilian Kohlbrenner, Alexander Bauer, Shinichi Nakajima, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin
Abstract Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in the novel field of explainable artificial intelligence (XAI). In this paper, we focus on a popular and widely used method of XAI, the Layer-wise Relevance Propagation (LRP). Since its initial proposition LRP has evolved as a method, and a best practice for applying the method has tacitly emerged, based however on humanly observed evidence alone. In this paper we investigate - and for the first time quantify - the effect of this current best practice on feedforward neural networks in a visual object detection setting. The results verify that the layer-dependent approach to LRP applied in recent literature better represents the model’s reasoning, and at the same time increases the object localization and class discriminativity of LRP.
Tasks Object Detection, Object Localization
Published 2019-10-22
URL https://arxiv.org/abs/1910.09840v2
PDF https://arxiv.org/pdf/1910.09840v2.pdf
PWC https://paperswithcode.com/paper/towards-best-practice-in-explaining-neural
Repo https://github.com/sebastian-lapuschkin/lrp_toolbox
Framework none

Neural Vector Conceptualization for Word Vector Space Interpretation

Title Neural Vector Conceptualization for Word Vector Space Interpretation
Authors Robert Schwarzenberg, Lisa Raithel, David Harbecke
Abstract Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method to interpret arbitrary samples from a word vector space. To this end, we train a neural model to conceptualize word vectors, which means that it activates higher order concepts it recognizes in a given vector. Contrary to prior approaches, our model operates in the original vector space and is capable of learning non-linear relations between word vectors and concepts. Furthermore, we show that it produces considerably less entropic concept activation profiles than the popular cosine similarity.
Tasks
Published 2019-04-02
URL http://arxiv.org/abs/1904.01500v1
PDF http://arxiv.org/pdf/1904.01500v1.pdf
PWC https://paperswithcode.com/paper/neural-vector-conceptualization-for-word
Repo https://github.com/dfki-nlp/nvc
Framework none

Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection

Title Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
Authors Deepak Babu Sam, Skand Vishwanath Peri, Mukuntha Narayanan Sundararaman, Amogh Kamath, R. Venkatesh Babu
Abstract We introduce a detection framework for dense crowd counting and eliminate the need for the prevalent density regression paradigm. Typical counting models predict crowd density for an image as opposed to detecting every person. These regression methods, in general, fail to localize persons accurate enough for most applications other than counting. Hence, we adopt an architecture that locates every person in the crowd, sizes the spotted heads with bounding box and then counts them. Compared to normal object or face detectors, there exist certain unique challenges in designing such a detection system. Some of them are direct consequences of the huge diversity in dense crowds along with the need to predict boxes contiguously. We solve these issues and develop our LSC-CNN model, which can reliably detect heads of people across sparse to dense crowds. LSC-CNN employs a multi-column architecture with top-down feedback processing to better resolve persons and produce refined predictions at multiple resolutions. Interestingly, the proposed training regime requires only point head annotation, but can estimate approximate size information of heads. We show that LSC-CNN not only has superior localization than existing density regressors, but outperforms in counting as well. The code for our approach is available at https://github.com/val-iisc/lsc-cnn.
Tasks Crowd Counting
Published 2019-06-18
URL https://arxiv.org/abs/1906.07538v3
PDF https://arxiv.org/pdf/1906.07538v3.pdf
PWC https://paperswithcode.com/paper/locate-size-and-count-accurately-resolving
Repo https://github.com/val-iisc/lsc-cnn
Framework pytorch
comments powered by Disqus