October 18, 2019

3088 words 15 mins read

Paper Group ANR 514

A Quantitative Evaluation of Natural Language Question Interpretation for Question Answering Systems. Multiview Two-Task Recursive Attention Model for Left Atrium and Atrial Scars Segmentation. Towards Resisting Large Data Variations via Introspective Learning. A high-performance analog Max-SAT solver and its application to Ramsey numbers. Simple R …

A Quantitative Evaluation of Natural Language Question Interpretation for Question Answering Systems


Title	A Quantitative Evaluation of Natural Language Question Interpretation for Question Answering Systems
Authors	Takuto Asakura, Jin-Dong Kim, Yasunori Yamamoto, Yuka Tateisi, Toshihisa Takagi
Abstract	Systematic benchmark evaluation plays an important role in the process of improving technologies for Question Answering (QA) systems. While currently there are a number of existing evaluation methods for natural language (NL) QA systems, most of them consider only the final answers, limiting their utility within a black box style evaluation. Herein, we propose a subdivided evaluation approach to enable finer-grained evaluation of QA systems, and present an evaluation tool which targets the NL question (NLQ) interpretation step, an initial step of a QA pipeline. The results of experiments using two public benchmark datasets suggest that we can get a deeper insight about the performance of a QA system using the proposed approach, which should provide a better guidance for improving the systems, than using black box style approaches.
Tasks	Question Answering
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07485v1
PDF	http://arxiv.org/pdf/1809.07485v1.pdf
PWC	https://paperswithcode.com/paper/a-quantitative-evaluation-of-natural-language
Repo
Framework

Multiview Two-Task Recursive Attention Model for Left Atrium and Atrial Scars Segmentation


Title	Multiview Two-Task Recursive Attention Model for Left Atrium and Atrial Scars Segmentation
Authors	Jun Chen, Guang Yang, Zhifan Gao, Hao Ni, Elsa Angelini, Raad Mohiaddin, Tom Wong, Yanping Zhang, Xiuquan Du, Heye Zhang, Jennifer Keegan, David Firmin
Abstract	Late Gadolinium Enhanced Cardiac MRI (LGE-CMRI) for detecting atrial scars in atrial fibrillation (AF) patients has recently emerged as a promising technique to stratify patients, guide ablation therapy and predict treatment success. Visualisation and quantification of scar tissues require a segmentation of both the left atrium (LA) and the high intensity scar regions from LGE-CMRI images. These two segmentation tasks are challenging due to the cancelling of healthy tissue signal, low signal-to-noise ratio and often limited image quality in these patients. Most approaches require manual supervision and/or a second bright-blood MRI acquisition for anatomical segmentation. Segmenting both the LA anatomy and the scar tissues automatically from a single LGE-CMRI acquisition is highly in demand. In this study, we proposed a novel fully automated multiview two-task (MVTT) recursive attention model working directly on LGE-CMRI images that combines a sequential learning and a dilated residual learning to segment the LA (including attached pulmonary veins) and delineate the atrial scars simultaneously via an innovative attention model. Compared to other state-of-the-art methods, the proposed MVTT achieves compelling improvement, enabling to generate a patient-specific anatomical and atrial scar assessment model.
Tasks
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04597v1
PDF	http://arxiv.org/pdf/1806.04597v1.pdf
PWC	https://paperswithcode.com/paper/multiview-two-task-recursive-attention-model
Repo
Framework

Towards Resisting Large Data Variations via Introspective Learning


Title	Towards Resisting Large Data Variations via Introspective Learning
Authors	Yunhan Zhao, Ye Tian, Wei Shen, Alan Yuille
Abstract	Learning deep networks which can resist large variations between training and testing data are essential to build accurate and robust image classifiers. Towards this end, a typical strategy is to apply data augmentation to enlarge the training set. However, standard data augmentation is essentially a brute-force method which is inefficient, as it performs all the pre-defined transformations to every training sample. In this paper, we propose a principled approach to train networks with significantly improved resistance to large variations between training and testing data. This is achieved by embedding a learnable transformation module into the introspective network, which is a convolutional neural network (CNN) classifier empowered with generative capabilities. Our approach alternatively synthesizes pseudo-negative samples with learned transformations and enhances the classifier by retraining it with synthesized samples. Experimental results verify that our approach significantly improves the ability of deep networks to resist large variations between training and testing data and achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN, CIFAR-10 and miniImageNet.
Tasks	Data Augmentation, Few-Shot Learning
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06447v2
PDF	http://arxiv.org/pdf/1805.06447v2.pdf
PWC	https://paperswithcode.com/paper/spatial-transformer-introspective-neural
Repo
Framework

A high-performance analog Max-SAT solver and its application to Ramsey numbers


Title	A high-performance analog Max-SAT solver and its application to Ramsey numbers
Authors	Botond Molnár, Melinda Varga, Zoltan Toroczkai, Mária Ercsey-Ravasz
Abstract	We introduce a continuous-time analog solver for MaxSAT, a quintessential class of NP-hard discrete optimization problems, where the task is to find a truth assignment for a set of Boolean variables satisfying the maximum number of given logical constraints. We show that the scaling of an invariant of the solver’s dynamics, the escape rate, as function of the number of unsatisfied clauses can predict the global optimum value, often well before reaching the corresponding state. We demonstrate the performance of the solver on hard MaxSAT competition problems. We then consider the two-color Ramsey number $R(m,m)$ problem, translate it to SAT, and apply our algorithm to the still unknown $R(5,5)$. We find edge colorings without monochromatic 5-cliques for complete graphs up to 42 vertices, while on 43 vertices we find colorings with only two monochromatic 5-cliques, the best coloring found so far, supporting the conjecture that $R(5,5) = 43$.
Tasks
Published	2018-01-20
URL	http://arxiv.org/abs/1801.06620v2
PDF	http://arxiv.org/pdf/1801.06620v2.pdf
PWC	https://paperswithcode.com/paper/a-high-performance-analog-max-sat-solver-and
Repo
Framework

Simple Regret Minimization for Contextual Bandits


Title	Simple Regret Minimization for Contextual Bandits
Authors	Aniket Anand Deshmukh, Srinagesh Sharma, James W. Cutler, Mark Moldwin, Clayton Scott
Abstract	There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side information that is predictive of the best arm. Simple regret minimization assumes that the learner only incurs regret after a pure exploration phase. In this work, we study simple regret minimization for contextual bandits. Motivated by applications where the learner has separate training and autonomous modes, we assume that the learner experiences a pure exploration phase, where feedback is received after every action but no regret is incurred, followed by a pure exploitation phase in which regret is incurred but there is no feedback. We present the Contextual-Gap algorithm and establish performance guarantees on the simple regret, i.e., the regret during the pure exploitation phase. Our experiments examine a novel application to adaptive sensor selection for magnetic field estimation in interplanetary spacecraft, and demonstrate considerable improvement over algorithms designed to minimize the cumulative regret.
Tasks	Multi-Armed Bandits
Published	2018-10-17
URL	https://arxiv.org/abs/1810.07371v2
PDF	https://arxiv.org/pdf/1810.07371v2.pdf
PWC	https://paperswithcode.com/paper/simple-regret-minimization-for-contextual
Repo
Framework

Interpreting Black Box Predictions using Fisher Kernels


Title	Interpreting Black Box Predictions using Fisher Kernels
Authors	Rajiv Khanna, Been Kim, Joydeep Ghosh, Oluwasanmi Koyejo
Abstract	Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models. To this end, we take a novel look at black box interpretation of test predictions in terms of training examples. Our goal is to ask `which training examples are most responsible for a given set of predictions’? To answer this question, we make use of Fisher kernels as the defining feature embedding of each data point, combined with Sequential Bayesian Quadrature (SBQ) for efficient selection of examples. In contrast to prior work, our method is able to seamlessly handle any sized subset of test predictions in a principled way. We theoretically analyze our approach, providing novel convergence bounds for SBQ over discrete candidate atoms. Our approach recovers the application of influence functions for interpretability as a special case yielding novel insights from this connection. We also present applications of the proposed approach to three use cases: cleaning training data, fixing mislabeled examples and data summarization. \|
Tasks	Data Summarization
Published	2018-10-23
URL	http://arxiv.org/abs/1810.10118v1
PDF	http://arxiv.org/pdf/1810.10118v1.pdf
PWC	https://paperswithcode.com/paper/interpreting-black-box-predictions-using
Repo
Framework

Network Modeling and Pathway Inference from Incomplete Data (“PathInf”)


Title	Network Modeling and Pathway Inference from Incomplete Data (“PathInf”)
Authors	Xiang Li, Qitian Chen, Xing Wang, Ning Guo, Nan Wu, Quanzheng Li
Abstract	In this work, we developed a network inference method from incomplete data (“PathInf”) , as massive and non-uniformly distributed missing values is a common challenge in practical problems. PathInf is a two-stages inference model. In the first stage, it applies a data summarization model based on maximum likelihood to deal with the massive distributed missing values by transforming the observation-wise items in the data into state matrix. In the second stage, transition pattern (i.e. pathway) among variables is inferred as a graph inference problem solved by greedy algorithm with constraints. The proposed method was validated and compared with the state-of-art Bayesian network method on the simulation data, and shown consistently superior performance. By applying the PathInf on the lymph vascular metastasis data, we obtained the holistic pathways of the lymph node metastasis with novel discoveries on the jumping metastasis among nodes that are physically apart. The discovery indicates the possible presence of sentinel node groups in the lung lymph nodes which have been previously speculated yet never found. The pathway map can also improve the current dissection examination protocol for better individualized treatment planning, for higher diagnostic accuracy and reducing the patients trauma.
Tasks	Data Summarization
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00839v1
PDF	http://arxiv.org/pdf/1810.00839v1.pdf
PWC	https://paperswithcode.com/paper/network-modeling-and-pathway-inference-from
Repo
Framework

Using solar and load predictions in battery scheduling at the residential level


Title	Using solar and load predictions in battery scheduling at the residential level
Authors	Richard Bean, Hina Khan
Abstract	Smart solar inverters can be used to store, monitor and manage a home’s solar energy. We describe a smart solar inverter system with battery which can either operate in an automatic mode or receive commands over a network to charge and discharge at a given rate. In order to make battery storage financially viable and advantageous to the consumers, effective battery scheduling algorithms can be employed. Particularly, when time-of-use tariffs are in effect in the region of the inverter, it is possible in some cases to schedule the battery to save money for the individual customer, compared to the “automatic” mode. Hence, this paper presents and evaluates the performance of a novel battery scheduling algorithm for residential consumers of solar energy. The proposed battery scheduling algorithm optimizes the cost of electricity over next 24 hours for residential consumers. The cost minimization is realized by controlling the charging/discharging of battery storage system based on the predictions for load and solar power generation values. The scheduling problem is formulated as a linear programming problem. We performed computer simulations over 83 inverters using several months of hourly load and PV data. The simulation results indicate that key factors affecting the viability of optimization are the tariffs and the PV to Load ratio at each inverter. Depending on the tariff, savings of between 1% and 10% can be expected over the automatic approach. The prediction approach used in this paper is also shown to out-perform basic “persistence” forecasting approaches. We have also examined the approaches for improving the prediction accuracy and optimization effectiveness.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11178v1
PDF	http://arxiv.org/pdf/1810.11178v1.pdf
PWC	https://paperswithcode.com/paper/using-solar-and-load-predictions-in-battery
Repo
Framework

Hallucinating robots: Inferring Obstacle Distances from Partial Laser Measurements


Title	Hallucinating robots: Inferring Obstacle Distances from Partial Laser Measurements
Authors	Jens Lundell, Francesco Verdoja, Ville Kyrki
Abstract	Many mobile robots rely on 2D laser scanners for localization, mapping, and navigation. However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the height the sensor is measuring. In this work, instead of estimating the distance to obstacles from richer sensor readings such as 3D lasers or RGBD sensors, we present a method to estimate the distance directly from raw 2D laser data. To learn a mapping from raw 2D laser distances to obstacle distances we frame the problem as a learning task and train a neural network formed as an autoencoder. A novel configuration of network hyperparameters is proposed for the task at hand and is quantitatively validated on a test set. Finally, we qualitatively demonstrate in real time on a Care-O-bot 4 that the trained network can successfully infer obstacle distances from partial 2D laser readings.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12338v2
PDF	http://arxiv.org/pdf/1805.12338v2.pdf
PWC	https://paperswithcode.com/paper/hallucinating-robots-inferring-obstacle
Repo
Framework

Learning to Become an Expert: Deep Networks Applied To Super-Resolution Microscopy


Title	Learning to Become an Expert: Deep Networks Applied To Super-Resolution Microscopy
Authors	Louis-Émile Robitaille, Audrey Durand, Marc-André Gardner, Christian Gagné, Paul De Koninck, Flavie Lavoie-Cardinal
Abstract	With super-resolution optical microscopy, it is now possible to observe molecular interactions in living cells. The obtained images have a very high spatial precision but their overall quality can vary a lot depending on the structure of interest and the imaging parameters. Moreover, evaluating this quality is often difficult for non-expert users. In this work, we tackle the problem of learning the quality function of super- resolution images from scores provided by experts. More specifically, we are proposing a system based on a deep neural network that can provide a quantitative quality measure of a STED image of neuronal structures given as input. We conduct a user study in order to evaluate the quality of the predictions of the neural network against those of a human expert. Results show the potential while highlighting some of the limits of the proposed approach.
Tasks	Super-Resolution
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10806v1
PDF	http://arxiv.org/pdf/1803.10806v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-become-an-expert-deep-networks
Repo
Framework

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition


Title	Geometry-Aware Recurrent Neural Networks for Active Visual Recognition
Authors	Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki
Abstract	We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene and latent feature locations. Object detection, object segmentation, and 3D reconstruction is then carried out directly using the constructed 3D feature memory, as opposed to any of the input 2D images. The proposed models are equipped with differentiable egomotion-aware feature warping and (learned) depth-aware unprojection operations to achieve geometrically consistent mapping between the features in the input frame and the constructed latent model of the scene. We empirically show the proposed model generalizes much better than geometryunaware LSTM/GRU networks, especially under the presence of multiple objects and cross-object occlusions. Combined with active view selection policies, our model learns to select informative viewpoints to integrate information from by “undoing” cross-object occlusions, seamlessly combining geometry with learning from experience.
Tasks	3D Reconstruction, Object Detection, Semantic Segmentation
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01292v2
PDF	http://arxiv.org/pdf/1811.01292v2.pdf
PWC	https://paperswithcode.com/paper/geometry-aware-recurrent-neural-networks-for
Repo
Framework

A Framework for Moment Invariants


Title	A Framework for Moment Invariants
Authors	Omar Tahri
Abstract	For more than half a century, moments have attracted lot ot interest in the pattern recognition community.The moments of a distribution (an object) provide several of its characteristics as center of gravity, orientation, disparity, volume. Moments can be used to define invariant characteristics to some transformations that an object can undergo, commonly called moment invariants. This work provides a simple and systematic formalism to compute geometric moment invariants in n-dimensional space.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06644v1
PDF	http://arxiv.org/pdf/1807.06644v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-moment-invariants
Repo
Framework

AdaFrame: Adaptive Frame Selection for Fast Video Recognition


Title	AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Authors	Zuxuan Wu, Caiming Xiong, Chih-Yao Ma, Richard Socher, Larry S. Davis
Abstract	We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network augmented with a global memory that provides context information for searching which frames to use over time. Trained with policy gradient methods, AdaFrame generates a prediction, determines which frame to observe next, and computes the utility, i.e., expected future rewards, of seeing more frames at each time step. At testing time, AdaFrame exploits predicted utilities to achieve adaptive lookahead inference such that the overall computational costs are reduced without incurring a decrease in accuracy. Extensive experiments are conducted on two large-scale video benchmarks, FCVID and ActivityNet. AdaFrame matches the performance of using all frames with only 8.21 and 8.65 frames on FCVID and ActivityNet, respectively. We further qualitatively demonstrate learned frame usage can indicate the difficulty of making classification decisions; easier samples need fewer frames while harder ones require more, both at instance-level within the same class and at class-level among different categories.
Tasks	Policy Gradient Methods, Video Recognition
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12432v2
PDF	http://arxiv.org/pdf/1811.12432v2.pdf
PWC	https://paperswithcode.com/paper/adaframe-adaptive-frame-selection-for-fast
Repo
Framework

Human Action Generation with Generative Adversarial Networks


Title	Human Action Generation with Generative Adversarial Networks
Authors	Mohammad Ahangar Kiasari, Dennis Singh Moirangthem, Minho Lee
Abstract	Inspired by the recent advances in generative models, we introduce a human action generation model in order to generate a consecutive sequence of human motions to formulate novel actions. We propose a framework of an autoencoder and a generative adversarial network (GAN) to produce multiple and consecutive human actions conditioned on the initial state and the given class label. The proposed model is trained in an end-to-end fashion, where the autoencoder is jointly trained with the GAN. The model is trained on the NTU RGB+D dataset and we show that the proposed model can generate different styles of actions. Moreover, the model can successfully generate a sequence of novel actions given different action labels as conditions. The conventional human action prediction and generation models lack those features, which are essential for practical applications.
Tasks	Human action generation
Published	2018-05-26
URL	http://arxiv.org/abs/1805.10416v1
PDF	http://arxiv.org/pdf/1805.10416v1.pdf
PWC	https://paperswithcode.com/paper/human-action-generation-with-generative
Repo
Framework

Knowledge Extracted from Recurrent Deep Belief Network for Real Time Deterministic Control


Title	Knowledge Extracted from Recurrent Deep Belief Network for Real Time Deterministic Control
Authors	Shin Kamada, Takumi Ichimura
Abstract	Recently, the market on deep learning including not only software but also hardware is developing rapidly. Big data is collected through IoT devices and the industry world will analyze them to improve their manufacturing process. Deep Learning has the hierarchical network architecture to represent the complicated features of input patterns. Although deep learning can show the high capability of classification, prediction, and so on, the implementation on GPU devices are required. We may meet the trade-off between the higher precision by deep learning and the higher cost with GPU devices. We can success the knowledge extraction from the trained deep learning with high classification capability. The knowledge that can realize faster inference of pre-trained deep network is extracted as IF-THEN rules from the network signal flow given input data. Some experiment results with benchmark tests for time series data sets showed the effectiveness of our proposed method related to the computational speed.
Tasks	Time Series
Published	2018-07-11
URL	http://arxiv.org/abs/1807.03954v1
PDF	http://arxiv.org/pdf/1807.03954v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-extracted-from-recurrent-deep
Repo
Framework