July 30, 2019

3055 words 15 mins read

Paper Group AWR 33

Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network. Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs. Fast Spectral Ranking for Similarity Search. Evaluating (and improving) the correspondence between deep neural networks and human representations …

Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network


Title	Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network
Authors	Dongsheng Jiang, Weiqiang Dou, Luc Vosters, Xiayu Xu, Yue Sun, Tao Tan
Abstract	The denoising of magnetic resonance (MR) images is a task of great importance for improving the acquired image quality. Many methods have been proposed in the literature to retrieve noise free images with good performances. Howerever, the state-of-the-art denoising methods, all needs a time-consuming optimization processes and their performance strongly depend on the estimated noise level parameter. Within this manuscript we propose the idea of denoising MRI Rician noise using a convolutional neural network. The advantage of the proposed methodology is that the learning based model can be directly used in the denosing process without optimization and even without the noise level parameter. Specifically, a ten convolutional layers neural network combined with residual learning and multi-channel strategy was proposed. Two training ways: training on a specific noise level and training on a general level were conducted to demonstrate the capability of our methods. Experimental results over synthetic and real 3D MR data demonstrate our proposed network can achieve superior performance compared with other methods in term of both of the peak signal to noise ratio and the global of structure similarity index. Without noise level parameter, our general noise-applicable model is also better than the other compared methods in two datasets. Furthermore, our training model shows good general applicability.
Tasks	Denoising
Published	2017-12-23
URL	http://arxiv.org/abs/1712.08726v2
PDF	http://arxiv.org/pdf/1712.08726v2.pdf
PWC	https://paperswithcode.com/paper/denoising-of-3d-magnetic-resonance-images
Repo	https://github.com/Dongshengjiang/Denoising-of-3D-magnetic-resonance-images-with-multi-channel-residual-CNN
Framework	none

Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs


Title	Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs
Authors	Rui Zhang, Honglak Lee, Lazaros Polymenakos, Dragomir Radev
Abstract	In this paper, we study the problem of addressee and response selection in multi-party conversations. Understanding multi-party conversations is challenging because of complex speaker interactions: multiple speakers exchange messages with each other, playing different roles (sender, addressee, observer), and these roles vary across turns. To tackle this challenge, we propose the Speaker Interaction Recurrent Neural Network (SI-RNN). Whereas the previous state-of-the-art system updated speaker embeddings only for the sender, SI-RNN uses a novel dialog encoder to update speaker embeddings in a role-sensitive way. Additionally, unlike the previous work that selected the addressee and response separately, SI-RNN selects them jointly by viewing the task as a sequence prediction problem. Experimental results show that SI-RNN significantly improves the accuracy of addressee and response selection, particularly in complex conversations with many speakers and responses to distant messages many turns in the past.
Tasks
Published	2017-09-12
URL	http://arxiv.org/abs/1709.04005v2
PDF	http://arxiv.org/pdf/1709.04005v2.pdf
PWC	https://paperswithcode.com/paper/addressee-and-response-selection-in-multi
Repo	https://github.com/ryanzhumich/sirnn
Framework	none

Fast Spectral Ranking for Similarity Search


Title	Fast Spectral Ranking for Similarity Search
Authors	Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum
Abstract	Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the manifolds online remains expensive even if a nearest neighbor graph has been computed offline. This work introduces an explicit embedding reducing manifold search to Euclidean search followed by dot product similarity search. This is equivalent to linear graph filtering of a sparse signal in the frequency domain. To speed up online search, we compute an approximate Fourier basis of the graph offline. We improve the state of art on particular object retrieval datasets including the challenging Instre dataset containing small objects. At a scale of 10^5 images, the offline cost is only a few hours, while query time is comparable to standard similarity search.
Tasks
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06935v3
PDF	http://arxiv.org/pdf/1703.06935v3.pdf
PWC	https://paperswithcode.com/paper/fast-spectral-ranking-for-similarity-search
Repo	https://github.com/ducha-aiki/manifold-diffusion
Framework	none

Evaluating (and improving) the correspondence between deep neural networks and human representations


Title	Evaluating (and improving) the correspondence between deep neural networks and human representations
Authors	Joshua C. Peterson, Joshua T. Abbott, Thomas L. Griffiths
Abstract	Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural networks have reached or surpassed human accuracy on tasks such as identifying objects in natural images. These networks learn representations of real-world stimuli that can potentially be leveraged to capture psychological representations. We find that state-of-the-art object classification networks provide surprisingly accurate predictions of human similarity judgments for natural images, but fail to capture some of the structure represented by people. We show that a simple transformation that corrects these discrepancies can be obtained through convex optimization. We use the resulting representations to predict the difficulty of learning novel categories of natural images. Our results extend the scope of psychological experiments and computational modeling by enabling tractable use of large natural stimulus sets.
Tasks	Object Classification
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02417v3
PDF	http://arxiv.org/pdf/1706.02417v3.pdf
PWC	https://paperswithcode.com/paper/evaluating-and-improving-the-correspondence
Repo	https://github.com/kbraunlich/contort_DNN
Framework	none

The Natural Stories Corpus


Title	The Natural Stories Corpus
Authors	Richard Futrell, Edward Gibson, Hal Tily, Idan Blank, Anastasia Vishnevetsky, Steven T. Piantadosi, Evelina Fedorenko
Abstract	It is now a common practice to compare models of human language processing by predicting participant reactions (such as reading times) to corpora consisting of rich naturalistic linguistic materials. However, many of the corpora used in these studies are based on naturalistic text and thus do not contain many of the low-frequency syntactic constructions that are often required to distinguish processing theories. Here we describe a new corpus consisting of English texts edited to contain many low-frequency syntactic constructions while still sounding fluent to native speakers. The corpus is annotated with hand-corrected parse trees and includes self-paced reading time data. Here we give an overview of the content of the corpus and release the data.
Tasks
Published	2017-08-18
URL	http://arxiv.org/abs/1708.05763v1
PDF	http://arxiv.org/pdf/1708.05763v1.pdf
PWC	https://paperswithcode.com/paper/the-natural-stories-corpus
Repo	https://github.com/languageMIT/naturalstories
Framework	none

Training Probabilistic Spiking Neural Networks with First-to-spike Decoding


Title	Training Probabilistic Spiking Neural Networks with First-to-spike Decoding
Authors	Alireza Bagheri, Osvaldo Simeone, Bipin Rajendran
Abstract	Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Generalized Linear Model (GLM) probabilistic neural model that was previously considered within the computational neuroscience literature. Conventional classification rules for SNNs operate offline based on the number of output spikes at each output neuron. In contrast, a novel training method is proposed here for a first-to-spike decoding rule, whereby the SNN can perform an early classification decision once spike firing is detected at an output neuron. Numerical results bring insights into the optimal parameter selection for the GLM neuron and on the accuracy-complexity trade-off performance of conventional and first-to-spike decoding.
Tasks
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10704v3
PDF	http://arxiv.org/pdf/1710.10704v3.pdf
PWC	https://paperswithcode.com/paper/training-probabilistic-spiking-neural
Repo	https://github.com/LucaMozzo/SpikingNeuralNetwork
Framework	none

Non-Count Symmetries in Boolean & Multi-Valued Prob. Graphical Models


Title	Non-Count Symmetries in Boolean & Multi-Valued Prob. Graphical Models
Authors	Ankit Anand, Ritesh Noothigattu, Parag Singla, Mausam
Abstract	Lifted inference algorithms commonly exploit symmetries in a probabilistic graphical model (PGM) for efficient inference. However, existing algorithms for Boolean-valued domains can identify only those pairs of states as symmetric, in which the number of ones and zeros match exactly (count symmetries). Moreover, algorithms for lifted inference in multi-valued domains also compute a multi-valued extension of count symmetries only. These algorithms miss many symmetries in a domain. In this paper, we present first algorithms to compute non-count symmetries in both Boolean-valued and multi-valued domains. Our methods can also find symmetries between multi-valued variables that have different domain cardinalities. The key insight in the algorithms is that they change the unit of symmetry computation from a variable to a variable-value (VV) pair. Our experiments find that exploiting these symmetries in MCMC can obtain substantial computational gains over existing algorithms.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08879v1
PDF	http://arxiv.org/pdf/1707.08879v1.pdf
PWC	https://paperswithcode.com/paper/non-count-symmetries-in-boolean-multi-valued
Repo	https://github.com/dair-iitd/nc-mcmc
Framework	none

Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task


Title	Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task
Authors	Stephen James, Andrew J. Davison, Edward Johns
Abstract	End-to-end control for robot manipulation and grasping is emerging as an attractive alternative to traditional pipelined approaches. However, end-to-end methods tend to either be slow to train, exhibit little or no generalisability, or lack the ability to accomplish long-horizon or multi-stage tasks. In this paper, we show how two simple techniques can lead to end-to-end (image to velocity) execution of a multi-stage task, which is analogous to a simple tidying routine, without having seen a single real image. This involves locating, reaching for, and grasping a cube, then locating a basket and dropping the cube inside. To achieve this, robot trajectories are computed in a simulator, to collect a series of control velocities which accomplish the task. Then, a CNN is trained to map observed images to velocities, using domain randomisation to enable generalisation to real world images. Results show that we are able to successfully accomplish the task in the real world with the ability to generalise to novel environments, including those with dynamic lighting conditions, distractor objects, and moving objects, including the basket itself. We believe our approach to be simple, highly scalable, and capable of learning long-horizon tasks that have until now not been shown with the state-of-the-art in end-to-end robot control.
Tasks	Robotic Grasping
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02267v2
PDF	http://arxiv.org/pdf/1707.02267v2.pdf
PWC	https://paperswithcode.com/paper/transferring-end-to-end-visuomotor-control
Repo	https://github.com/stepjam/PyRep
Framework	none

Streamlined Deployment for Quantized Neural Networks


Title	Streamlined Deployment for Quantized Neural Networks
Authors	Yaman Umuroglu, Magnus Jahre
Abstract	Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem, promising to offer most of the DNN accuracy benefits with much lower computational cost. However, harvesting these benefits on existing mobile CPUs is a challenge since operations on highly quantized datatypes are not natively supported in most instruction set architectures (ISAs). In this work, we first describe a streamlining flow to convert all QNN inference operations to integer ones. Afterwards, we provide techniques based on processing one bit position at a time (bit-serial) to show how QNNs can be efficiently deployed using common bitwise operations. We demonstrate the potential of QNNs on mobile CPUs with microbenchmarks and on a quantized AlexNet, which is 3.5x faster than an optimized 8-bit baseline. Our bit-serial matrix multiplication library is available on GitHub at https://git.io/vhshn
Tasks
Published	2017-09-12
URL	http://arxiv.org/abs/1709.04060v2
PDF	http://arxiv.org/pdf/1709.04060v2.pdf
PWC	https://paperswithcode.com/paper/streamlined-deployment-for-quantized-neural
Repo	https://github.com/EECS-NTNU/bismo
Framework	none

Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks


Title	Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
Authors	Pranav Rajpurkar, Awni Y. Hannun, Masoumeh Haghpanahi, Codie Bourn, Andrew Y. Ng
Abstract	We develop an algorithm which exceeds the performance of board certified cardiologists in detecting a wide range of heart arrhythmias from electrocardiograms recorded with a single-lead wearable monitor. We build a dataset with more than 500 times the number of unique patients than previously studied corpora. On this dataset, we train a 34-layer convolutional neural network which maps a sequence of ECG samples to a sequence of rhythm classes. Committees of board-certified cardiologists annotate a gold standard test set on which we compare the performance of our model to that of 6 other individual cardiologists. We exceed the average cardiologist performance in both recall (sensitivity) and precision (positive predictive value).
Tasks	Arrhythmia Detection, Electrocardiography (ECG)
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01836v1
PDF	http://arxiv.org/pdf/1707.01836v1.pdf
PWC	https://paperswithcode.com/paper/cardiologist-level-arrhythmia-detection-with
Repo	https://github.com/VinGPan/paper_implementations
Framework	tf

Motion Compensated Dynamic MRI Reconstruction with Local Affine Optical Flow Estimation


Title	Motion Compensated Dynamic MRI Reconstruction with Local Affine Optical Flow Estimation
Authors	Ningning Zhao, Daniel O’Connor, Adrian Basarab, Dan Ruan, Peng Hu, Ke Sheng
Abstract	This paper proposes a novel framework to reconstruct the dynamic magnetic resonance images (DMRI) with motion compensation (MC). Due to the inherent motion effects during DMRI acquisition, reconstruction of DMRI using motion estimation/compensation (ME/MC) has been studied under a compressed sensing (CS) scheme. In this paper, by embedding the intensity-based optical flow (OF) constraint into the traditional CS scheme, we are able to couple the DMRI reconstruction with motion field estimation. The formulated optimization problem is solved by a primal-dual algorithm with linesearch due to its efficiency when dealing with non-differentiable problems. With the estimated motion field, the DMRI reconstruction is refined through MC. By employing the multi-scale coarse-to-fine strategy, we are able to update the variables(temporal image sequences and motion vectors) and to refine the image reconstruction alternately. Moreover, the proposed framework is capable of handling a wide class of prior information (regularizations) for DMRI reconstruction, such as sparsity, low rank and total variation. Experiments on various DMRI data, ranging from in vivo lung to cardiac dataset, validate the reconstruction quality improvement using the proposed scheme in comparison to several state-of-the-art algorithms.
Tasks	Image Reconstruction, Motion Compensation, Motion Estimation, Optical Flow Estimation
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07089v3
PDF	http://arxiv.org/pdf/1707.07089v3.pdf
PWC	https://paperswithcode.com/paper/motion-compensated-dynamic-mri-reconstruction
Repo	https://github.com/ning22/Motion-Compensated-Dynamic-MRI-Reconstruction-with-Local-Affine-Optical-Flow-Estimation
Framework	none

Residual Gated Graph ConvNets


Title	Residual Gated Graph ConvNets
Authors	Xavier Bresson, Thomas Laurent
Abstract	Graph-structured data such as social networks, functional brain networks, gene regulatory networks, communications networks have brought the interest in generalizing deep learning techniques to graph domains. In this paper, we are interested to design neural networks for graphs with variable length in order to solve learning problems such as vertex classification, graph classification, graph regression, and graph generative tasks. Most existing works have focused on recurrent neural networks (RNNs) to learn meaningful representations of graphs, and more recently new convolutional neural networks (ConvNets) have been introduced. In this work, we want to compare rigorously these two fundamental families of architectures to solve graph learning tasks. We review existing graph RNN and ConvNet architectures, and propose natural extension of LSTM and ConvNet to graphs with arbitrary size. Then, we design a set of analytically controlled experiments on two basic graph problems, i.e. subgraph matching and graph clustering, to test the different architectures. Numerical results show that the proposed graph ConvNets are 3-17% more accurate and 1.5-4x faster than graph RNNs. Graph ConvNets are also 36% more accurate than variational (non-learning) techniques. Finally, the most effective graph ConvNet architecture uses gated edges and residuality. Residuality plays an essential role to learn multi-layer architectures as they provide a 10% gain of performance.
Tasks	Graph Classification, Graph Clustering, Graph Regression
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07553v2
PDF	http://arxiv.org/pdf/1711.07553v2.pdf
PWC	https://paperswithcode.com/paper/residual-gated-graph-convnets
Repo	https://github.com/xbresson/spatial_graph_convnets
Framework	pytorch

Convolutional Normalizing Flows


Title	Convolutional Normalizing Flows
Authors	Guoqing Zheng, Yiming Yang, Jaime Carbonell
Abstract	Bayesian posterior inference is prevalent in various machine learning problems. Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting approximation. Recently, there has a trend of using neural networks to approximate the variational posterior distribution due to the flexibility of neural network architecture. One way to construct flexible variational distribution is to warp a simple density into a complex by normalizing flows, where the resulting density can be analytically evaluated. However, there is a trade-off between the flexibility of normalizing flow and computation cost for efficient transformation. In this paper, we propose a simple yet effective architecture of normalizing flows, ConvFlow, based on convolution over the dimensions of random input vector. Experiments on synthetic and real world posterior inference problems demonstrate the effectiveness and efficiency of the proposed method.
Tasks
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02255v2
PDF	http://arxiv.org/pdf/1711.02255v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-normalizing-flows
Repo	https://github.com/apsyx/mvae
Framework	pytorch

Adversarially Regularized Autoencoders


Title	Adversarially Regularized Autoencoders
Authors	Jake Zhao, Yoon Kim, Kelly Zhang, Alexander M. Rush, Yann LeCun
Abstract	Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures, such as text sequences or discretized images, has proven to be more challenging. In this work, we propose a flexible method for training deep latent variable models of discrete structures. Our approach is based on the recently-proposed Wasserstein autoencoder (WAE) which formalizes the adversarial autoencoder (AAE) as an optimal transport problem. We first extend this framework to model discrete sequences, and then further explore different learned priors targeting a controllable representation. This adversarially regularized autoencoder (ARAE) allows us to generate natural textual outputs as well as perform manipulations in the latent space to induce change in the output space. Finally we show that the latent representation can be trained to perform unaligned textual style transfer, giving improvements both in automatic/human evaluation compared to existing methods.
Tasks	Latent Variable Models, Representation Learning, Style Transfer
Published	2017-06-13
URL	http://arxiv.org/abs/1706.04223v3
PDF	http://arxiv.org/pdf/1706.04223v3.pdf
PWC	https://paperswithcode.com/paper/adversarially-regularized-autoencoders
Repo	https://github.com/jakezhaojb/ARAE
Framework	pytorch

Accurate Real Time Localization Tracking in A Clinical Environment using Bluetooth Low Energy and Deep Learning


Title	Accurate Real Time Localization Tracking in A Clinical Environment using Bluetooth Low Energy and Deep Learning
Authors	Zohaib Iqbal, Da Luo, Peter Henry, Samaneh Kazemifar, Timothy Rozario, Yulong Yan, Kenneth Westover, Weiguo Lu, Dan Nguyen, Troy Long, Jing Wang, Hak Choy, Steve Jiang
Abstract	Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.
Tasks
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08149v3
PDF	http://arxiv.org/pdf/1711.08149v3.pdf
PWC	https://paperswithcode.com/paper/accurate-real-time-localization-tracking-in-a
Repo	https://github.com/zoball/BLE-Tracking-with-Deep-Learning
Framework	none