Paper Group ANR 808
Visualization Framework for Colonoscopy Videos. Hybrid Self-Attention Network for Machine Translation. Crowd Sourcing based Active Learning Approach for Parking Sign Recognition. Efficient random graph matching via degree profiles. 3D Path Planning from a Single 2D Fluoroscopic Image for Robot Assisted Fenestrated Endovascular Aortic Repair. Double …
Visualization Framework for Colonoscopy Videos
| Title | Visualization Framework for Colonoscopy Videos |
| Authors | Saad Nadeem, Arie Kaufman |
| Abstract | We present a visualization framework for annotating and comparing colonoscopy videos, where these annotations can then be used for semi-automatic report generation at the end of the procedure. Currently, there are approximately 14 million colonoscopies performed every year in the US. In this work, we create a visualization tool to deal with the deluge of colonoscopy videos in a more effective way. We present an interactive visualization framework for the annotation and tagging of colonoscopy videos in an easy and intuitive way. These annotations and tags can later be used for report generation for electronic medical records and for comparison at an individual as well as group level. We also present important use cases and medical expert feedback for our visualization framework. |
| Tasks | |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.08998v1 |
| http://arxiv.org/pdf/1810.08998v1.pdf | |
| PWC | https://paperswithcode.com/paper/visualization-framework-for-colonoscopy |
| Repo | |
| Framework | |
Hybrid Self-Attention Network for Machine Translation
| Title | Hybrid Self-Attention Network for Machine Translation |
| Authors | Kaitao Song, Xu Tan, Furong Peng, Jianfeng Lu |
| Abstract | The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can leverage the self-attention mechanism to capture the semantic dependency from global view. However, it cannot distinguish the relative position of different tokens very well, such as the tokens located at the left or right of the current token, and cannot focus on the local information around the current token either. To alleviate these problems, we propose a novel attention mechanism named Hybrid Self-Attention Network (HySAN) which accommodates some specific-designed masks for self-attention network to extract various semantic, such as the global/local information, the left/right part context. Finally, a squeeze gate is introduced to combine different kinds of SANs for fusion. Experimental results on three machine translation tasks show that our proposed framework outperforms the Transformer baseline significantly and achieves superior results over state-of-the-art NMT systems. |
| Tasks | Machine Translation |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.00253v3 |
| http://arxiv.org/pdf/1811.00253v3.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-self-attention-network-for-machine |
| Repo | |
| Framework | |
Crowd Sourcing based Active Learning Approach for Parking Sign Recognition
| Title | Crowd Sourcing based Active Learning Approach for Parking Sign Recognition |
| Authors | Humayun Irshad, Qazaleh Mirsharif, Jennifer Prendki |
| Abstract | Deep learning models have been used extensively to solve real-world problems in recent years. The performance of such models relies heavily on large amounts of labeled data for training. While the advances of data collection technology have enabled the acquisition of a massive volume of data, labeling the data remains an expensive and time-consuming task. Active learning techniques are being progressively adopted to accelerate the development of machine learning solutions by allowing the model to query the data they learn from. In this paper, we introduce a real-world problem, the recognition of parking signs, and present a framework that combines active learning techniques with a transfer learning approach and crowd-sourcing tools to create and train a machine learning solution to the problem. We discuss how such a framework contributes to building an accurate model in a cost-effective and fast way to solve the parking sign recognition problem in spite of the unevenness of the data associated with the fact that street-level images (such as parking signs) vary in shape, color, orientation and scale, and often appear on top of different types of background. |
| Tasks | Active Learning, Transfer Learning |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.01081v1 |
| http://arxiv.org/pdf/1812.01081v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-sourcing-based-active-learning-approach |
| Repo | |
| Framework | |
Efficient random graph matching via degree profiles
| Title | Efficient random graph matching via degree profiles |
| Authors | Jian Ding, Zongming Ma, Yihong Wu, Jiaming Xu |
| Abstract | Random graph matching refers to recovering the underlying vertex correspondence between two random graphs with correlated edges; a prominent example is when the two random graphs are given by Erd\H{o}s-R'{e}nyi graphs $G(n,\frac{d}{n})$. This can be viewed as an average-case and noisy version of the graph isomorphism problem. Under this model, the maximum likelihood estimator is equivalent to solving the intractable quadratic assignment problem. This work develops an $\tilde{O}(n d^2+n^2)$-time algorithm which perfectly recovers the true vertex correspondence with high probability, provided that the average degree is at least $d = \Omega(\log^2 n)$ and the two graphs differ by at most $\delta = O( \log^{-2}(n) )$ fraction of edges. For dense graphs and sparse graphs, this can be improved to $\delta = O( \log^{-2/3}(n) )$ and $\delta = O( \log^{-2}(d) )$ respectively, both in polynomial time. The methodology is based on appropriately chosen distance statistics of the degree profiles (empirical distribution of the degrees of neighbors). Before this work, the best known result achieves $\delta=O(1)$ and $n^{o(1)} \leq d \leq n^c$ for some constant $c$ with an $n^{O(\log n)}$-time algorithm \cite{barak2018nearly} and $\delta=\tilde O((d/n)^4)$ and $d = \tilde{\Omega}(n^{4/5})$ with a polynomial-time algorithm \cite{dai2018performance}. |
| Tasks | Graph Matching |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07821v1 |
| http://arxiv.org/pdf/1811.07821v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-random-graph-matching-via-degree |
| Repo | |
| Framework | |
3D Path Planning from a Single 2D Fluoroscopic Image for Robot Assisted Fenestrated Endovascular Aortic Repair
| Title | 3D Path Planning from a Single 2D Fluoroscopic Image for Robot Assisted Fenestrated Endovascular Aortic Repair |
| Authors | Jian-Qing Zheng, Xiao-Yun Zhou, Celia Riga, Guang-Zhong Yang |
| Abstract | The current standard of intra-operative navigation during Fenestrated Endovascular Aortic Repair (FEVAR) calls for need of 3D alignments between inserted devices and aortic branches. The navigation commonly via 2D fluoroscopic images, lacks anatomical information, resulting in longer operation hours and radiation exposure. In this paper, a framework for real-time 3D robotic path planning from a single 2D fluoroscopic image of Abdominal Aortic Aneurysm (AAA) is introduced. A graph matching method is proposed to establish the correspondence between the 3D preoperative and 2D intra-operative AAA skeletons, and then the two skeletons are registered by skeleton deformation and regularization in respect to skeleton length and smoothness. Furthermore, deep learning was used to segment 3D pre-operative AAA from Computed Tomography (CT) scans to facilitate the framework automation. Simulation, phantom and patient AAA data sets have been used to validate the proposed framework. 3D distance error of 2mm was achieved in the phantom setup. Performance advantages were also achieved in terms of accuracy, robustness and time-efficiency. All the code will be open source. |
| Tasks | Computed Tomography (CT), Graph Matching |
| Published | 2018-09-16 |
| URL | http://arxiv.org/abs/1809.05955v1 |
| http://arxiv.org/pdf/1809.05955v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-path-planning-from-a-single-2d |
| Repo | |
| Framework | |
Double/De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers
| Title | Double/De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers |
| Authors | Victor Chernozhukov, Whitney Newey, James Robins |
| Abstract | We provide adaptive inference methods, based on l1 regularization methods, for regular (semi-parametric) and non-regular (nonparametric) linear functionals of the conditional expectation function. Examples of regular functionals include average treatment effects, policy effects from covariate distribution shifts and stochastic transformations, and average derivatives. Examples of non-regular functionals include the local linear functionals defined as local averages that approximate perfectly localized quantities: average treatment, average policy effects, and average derivatives, conditional on a covariate subvector fixed at a point. Our construction relies on building Neyman orthogonal equations for the target parameter that are approximately invariant to small perturbations of the nuisance parameters. To achieve this property we include the linear Riesz representer for the functionals in the equations as the additional nuisance parameter. We use l1-regularized methods to learn approximations to the regression function and the linear representer, in settings where dimension of (possibly overcomplete) dictionary of basis functions P is much larger than N. We then estimate the linear functional by the solution to the empirical analog of the orthogonal equations. Our key result is that under weak assumptions the estimator of the functional concentrates in a L/root(n) neighborhood of the target with deviations controlled by the Gaussian law, provided L/root(n) \to 0; L is the operator norm of the functional, measuring the degree of its non-regularity, with L diverging for local functionals (or under weak identification of the global functionals). |
| Tasks | |
| Published | 2018-02-23 |
| URL | https://arxiv.org/abs/1802.08667v3 |
| https://arxiv.org/pdf/1802.08667v3.pdf | |
| PWC | https://paperswithcode.com/paper/doublede-biased-machine-learning-using |
| Repo | |
| Framework | |
Elastic Registration of Geodesic Vascular Graphs
| Title | Elastic Registration of Geodesic Vascular Graphs |
| Authors | Stefano Moriconi, Maria A. Zuluaga, H. Rolf Jager, Parashkev Nachev, Sebastien Ourselin, M. Jorge Cardoso |
| Abstract | Vascular graphs can embed a number of high-level features, from morphological parameters, to functional biomarkers, and represent an invaluable tool for longitudinal and cross-sectional clinical inference. This, however, is only feasible when graphs are co-registered together, allowing coherent multiple comparisons. The robust registration of vascular topologies stands therefore as key enabling technology for group-wise analyses. In this work, we present an end-to-end vascular graph registration approach, that aligns networks with non-linear geometries and topological deformations, by introducing a novel overconnected geodesic vascular graph formulation, and without enforcing any anatomical prior constraint. The 3D elastic graph registration is then performed with state-of-the-art graph matching methods used in computer vision. Promising results of vascular matching are found using graphs from synthetic and real angiographies. Observations and future designs are discussed towards potential clinical applications. |
| Tasks | Graph Matching |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.05499v1 |
| http://arxiv.org/pdf/1809.05499v1.pdf | |
| PWC | https://paperswithcode.com/paper/elastic-registration-of-geodesic-vascular |
| Repo | |
| Framework | |
Convolutional Neural Networks for Fast Approximation of Graph Edit Distance
| Title | Convolutional Neural Networks for Fast Approximation of Graph Edit Distance |
| Authors | Yunsheng Bai, Hao Ding, Yizhou Sun, Wei Wang |
| Abstract | Graph Edit Distance (GED) computation is a core operation of many widely-used graph applications, such as graph classification, graph matching, and graph similarity search. However, computing the exact GED between two graphs is NP-complete. Most current approximate algorithms are based on solving a combinatorial optimization problem, which involves complicated design and high time complexity. In this paper, we propose a novel end-to-end neural network based approach to GED approximation, aiming to alleviate the computational burden while preserving good performance. The proposed approach, named GSimCNN, turns GED computation into a learning problem. Each graph is considered as a set of nodes, represented by learnable embedding vectors. The GED computation is then considered as a two-set matching problem, where a higher matching score leads to a lower GED. A Convolutional Neural Network (CNN) based approach is proposed to tackle the set matching problem. We test our algorithm on three real graph datasets, and our model achieves significant performance enhancement against state-of-the-art approximate GED computation algorithms. |
| Tasks | Combinatorial Optimization, Graph Classification, Graph Matching, Graph Similarity |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.04440v1 |
| http://arxiv.org/pdf/1809.04440v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-fast |
| Repo | |
| Framework | |
Parsing Coordination for Spoken Language Understanding
| Title | Parsing Coordination for Spoken Language Understanding |
| Authors | Sanchit Agarwal, Rahul Goel, Tagyoung Chung, Abhishek Sethi, Arindam Mandal, Spyros Matsoukas |
| Abstract | Typical spoken language understanding systems provide narrow semantic parses using a domain-specific ontology. The parses contain intents and slots that are directly consumed by downstream domain applications. In this work we discuss expanding such systems to handle compound entities and intents by introducing a domain-agnostic shallow parser that handles linguistic coordination. We show that our model for parsing coordination learns domain-independent and slot-independent features and is able to segment conjunct boundaries of many different phrasal categories. We also show that using adversarial training can be effective for improving generalization across different slot types for coordination parsing. |
| Tasks | Spoken Language Understanding |
| Published | 2018-10-26 |
| URL | http://arxiv.org/abs/1810.11497v1 |
| http://arxiv.org/pdf/1810.11497v1.pdf | |
| PWC | https://paperswithcode.com/paper/parsing-coordination-for-spoken-language |
| Repo | |
| Framework | |
Gaussian variational approximation for high-dimensional state space models
| Title | Gaussian variational approximation for high-dimensional state space models |
| Authors | Matias Quiroz, David J. Nott, Robert Kohn |
| Abstract | Our article considers a Gaussian variational approximation of the posterior density in a high-dimensional state space model. The variational parameters to be optimized are the mean vector and the covariance matrix of the approximation. The number of parameters in the covariance matrix grows as the square of the number of model parameters, so it is necessary to find simple yet effective parameterizations of the covariance structure when the number of model parameters is large. We approximate the joint posterior distribution over the high-dimensional state vectors by a dynamic factor model, having Markovian time dependence and a factor covariance structure for the states. This gives a reduced description of the dependence structure for the states, as well as a temporal conditional independence structure similar to that in the true posterior. The usefulness of the approach is illustrated for prediction in two high-dimensional applications that are challenging for Markov chain Monte Carlo sampling. The first is a spatio-temporal model for the spread of the Eurasian Collared-Dove across North America; the second is a Wishart-based multivariate stochastic volatility model for financial returns. |
| Tasks | |
| Published | 2018-01-24 |
| URL | https://arxiv.org/abs/1801.07873v3 |
| https://arxiv.org/pdf/1801.07873v3.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-variational-approximation-for-high |
| Repo | |
| Framework | |
An interpretable LSTM neural network for autoregressive exogenous model
| Title | An interpretable LSTM neural network for autoregressive exogenous model |
| Authors | Tian Guo, Tao Lin, Yao Lu |
| Abstract | In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To this end, our multi-variable LSTM equipped with tensorized hidden states is developed to learn variable specific representations, which give rise to both temporal and variable level attention. Preliminary experiments demonstrate comparable prediction performance of multi-variable LSTM w.r.t. encoder-decoder based baselines. More interestingly, variable importance in real datasets characterized by the variable attention is highly in line with that determined by statistical Granger causality test, which exhibits the prospect of multi-variable LSTM as a simple and uniform end-to-end framework for both forecasting and knowledge discovery. |
| Tasks | Time Series |
| Published | 2018-04-14 |
| URL | http://arxiv.org/abs/1804.05251v1 |
| http://arxiv.org/pdf/1804.05251v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-interpretable-lstm-neural-network-for |
| Repo | |
| Framework | |
Mod-DeepESN: Modular Deep Echo State Network
| Title | Mod-DeepESN: Modular Deep Echo State Network |
| Authors | Zachariah Carmichael, Humza Syed, Stuart Burtner, Dhireesha Kudithipudi |
| Abstract | Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex tasks that are characterized by multi-scale structures. In this research, an intrinsic plasticity-infused modular deep echo state network architecture is proposed to solve complex and multiple timescale temporal tasks. It outperforms state-of-the-art for time series prediction tasks. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00523v2 |
| http://arxiv.org/pdf/1808.00523v2.pdf | |
| PWC | https://paperswithcode.com/paper/mod-deepesn-modular-deep-echo-state-network |
| Repo | |
| Framework | |
A Generative Model for Dynamic Networks with Applications
| Title | A Generative Model for Dynamic Networks with Applications |
| Authors | Shubham Gupta, Gaurav Sharma, Ambedkar Dukkipati |
| Abstract | Networks observed in real world like social networks, collaboration networks etc., exhibit temporal dynamics, i.e. nodes and edges appear and/or disappear over time. In this paper, we propose a generative, latent space based, statistical model for such networks (called dynamic networks). We consider the case where the number of nodes is fixed, but the presence of edges can vary over time. Our model allows the number of communities in the network to be different at different time steps. We use a neural network based methodology to perform approximate inference in the proposed model and its simplified version. Experiments done on synthetic and real world networks for the task of community detection and link prediction demonstrate the utility and effectiveness of our model as compared to other similar existing approaches. |
| Tasks | Community Detection, Link Prediction |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03725v2 |
| http://arxiv.org/pdf/1802.03725v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-generative-model-for-dynamic-networks-with |
| Repo | |
| Framework | |
Distance entropy cartography characterises centrality in complex networks
| Title | Distance entropy cartography characterises centrality in complex networks |
| Authors | Massimo Stella, Manlio De Domenico |
| Abstract | We introduce distance entropy as a measure of homogeneity in the distribution of path lengths between a given node and its neighbours in a complex network. Distance entropy defines a new centrality measure whose properties are investigated for a variety of synthetic network models. By coupling distance entropy information with closeness centrality, we introduce a network cartography which allows one to reduce the degeneracy of ranking based on closeness alone. We apply this methodology to the empirical multiplex lexical network encoding the linguistic relationships known to English speaking toddlers. We show that the distance entropy cartography better predicts how children learn words compared to closeness centrality. Our results highlight the importance of distance entropy for gaining insights from distance patterns in complex networks. |
| Tasks | |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1802.10411v1 |
| http://arxiv.org/pdf/1802.10411v1.pdf | |
| PWC | https://paperswithcode.com/paper/distance-entropy-cartography-characterises |
| Repo | |
| Framework | |
Meta-Learning by the Baldwin Effect
| Title | Meta-Learning by the Baldwin Effect |
| Authors | Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, Andrei A. Rusu |
| Abstract | The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstration of its necessity in empirically challenging tasks. Here we show that the Baldwin effect is capable of evolving few-shot supervised and reinforcement learning mechanisms, by shaping the hyperparameters and the initial parameters of deep learning algorithms. Furthermore it can genetically accommodate strong learning biases on the same set of problems as a recent machine learning algorithm called MAML “Model Agnostic Meta-Learning” which uses second-order gradients instead of evolution to learn a set of reference parameters (initial weights) that can allow rapid adaptation to tasks sampled from a distribution. Whilst in simple cases MAML is more data efficient than the Baldwin effect, the Baldwin effect is more general in that it does not require gradients to be backpropagated to the reference parameters or hyperparameters, and permits effectively any number of gradient updates in the inner loop. The Baldwin effect learns strong learning dependent biases, rather than purely genetically accommodating fixed behaviours in a learning independent manner. |
| Tasks | Meta-Learning |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.07917v2 |
| http://arxiv.org/pdf/1806.07917v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-by-the-baldwin-effect |
| Repo | |
| Framework | |
