July 27, 2019

2769 words 13 mins read

Paper Group ANR 618

K-means clustering for efficient and robust registration of multi-view point sets. Spatial-temporal wind field prediction by Artificial Neural Networks. The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment. Active Exploration for Learning Symbolic Representations. A Modification of Particle Swarm Opt …

K-means clustering for efficient and robust registration of multi-view point sets


Title	K-means clustering for efficient and robust registration of multi-view point sets
Authors	Zutao Jiang, Jihua Zhu, Georgios D. Evangelidis, Changqing Zhang, Shanmin Pang, Yaochen Li
Abstract	Generally, there are three main factors that determine the practical usability of registration, i.e., accuracy, robustness, and efficiency. In real-time applications, efficiency and robustness are more important. To promote these two abilities, we cast the multi-view registration into a clustering task. All the centroids are uniformly sampled from the initially aligned point sets involved in the multi-view registration, which makes it rather efficient and effective for the clustering. Then, each point is assigned to a single cluster and each cluster centroid is updated accordingly. Subsequently, the shape comprised by all cluster centroids is used to sequentially estimate the rigid transformation for each point set. For accuracy and stability, clustering and transformation estimation are alternately and iteratively applied to all point sets. We tested our proposed approach on several benchmark datasets and compared it with state-of-the-art approaches. Experimental results validate its efficiency and robustness for the registration of multi-view point sets.
Tasks
Published	2017-10-14
URL	http://arxiv.org/abs/1710.05193v4
PDF	http://arxiv.org/pdf/1710.05193v4.pdf
PWC	https://paperswithcode.com/paper/k-means-clustering-for-efficient-and-robust
Repo
Framework

Spatial-temporal wind field prediction by Artificial Neural Networks


Title	Spatial-temporal wind field prediction by Artificial Neural Networks
Authors	Jianan Cao, David J. Farnham, Upmanu Lall
Abstract	The prediction of near surface wind speed is becoming increasingly vital for the operation of electrical energy grids as the capacity of installed wind power grows. The majority of predictive wind speed modeling has focused on point-based time-series forecasting. Effectively balancing demand and supply in the presence of distributed wind turbine electricity generation, however, requires the prediction of wind fields in space and time. Additionally, predictions of full wind fields are particularly useful for future power planning such as the optimization of electricity power supply systems. In this paper, we propose a composite artificial neural network (ANN) model to predict the 6-hour and 24-hour ahead average wind speed over a large area (~3.15*106 km2). The ANN model consists of a convolutional input layer, a Long Short-Term Memory (LSTM) hidden layer, and a transposed convolutional layer as the output layer. We compare the ANN model with two non-parametric models, a null persistence model and a mean value model, and find that the ANN model has substantially smaller error than each of these models. Additionally, the ANN model also generally performs better than integrated autoregressive moving average models, which are trained for optimal performance in specific locations.
Tasks	Time Series, Time Series Forecasting
Published	2017-12-13
URL	http://arxiv.org/abs/1712.05293v1
PDF	http://arxiv.org/pdf/1712.05293v1.pdf
PWC	https://paperswithcode.com/paper/spatial-temporal-wind-field-prediction-by
Repo
Framework

The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment


Title	The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment
Authors	Angus Galloway, Graham W. Taylor, Aaron Ramsay, Medhat Moussa
Abstract	An original dataset for semantic segmentation, Ciona17, is introduced, which to the best of the authors’ knowledge, is the first dataset of its kind with pixel-level annotations pertaining to invasive species in a marine environment. Diverse outdoor illumination, a range of object shapes, colour, and severe occlusion provide a significant real world challenge for the computer vision community. An accompanying ground-truthing tool for superpixel labeling, Truth and Crop, is also introduced. Finally, we provide a baseline using a variant of Fully Convolutional Networks, and report results in terms of the standard mean intersection over union (mIoU) metric.
Tasks	Semantic Segmentation
Published	2017-02-18
URL	http://arxiv.org/abs/1702.05564v1
PDF	http://arxiv.org/pdf/1702.05564v1.pdf
PWC	https://paperswithcode.com/paper/the-ciona17-dataset-for-semantic-segmentation
Repo
Framework

Active Exploration for Learning Symbolic Representations


Title	Active Exploration for Learning Symbolic Representations
Authors	Garrett Andersen, George Konidaris
Abstract	We introduce an online active exploration algorithm for data-efficiently learning an abstract symbolic model of an environment. Our algorithm is divided into two parts: the first part quickly generates an intermediate Bayesian symbolic model from the data that the agent has collected so far, which the agent can then use along with the second part to guide its future exploration towards regions of the state space that the model is uncertain about. We show that our algorithm outperforms random and greedy exploration policies on two different computer game domains. The first domain is an Asteroids-inspired game with complex dynamics but basic logical structure. The second is the Treasure Game, with simpler dynamics but more complex logical structure.
Tasks
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01490v2
PDF	http://arxiv.org/pdf/1709.01490v2.pdf
PWC	https://paperswithcode.com/paper/active-exploration-for-learning-symbolic
Repo
Framework

A Modification of Particle Swarm Optimization using Random Walk


Title	A Modification of Particle Swarm Optimization using Random Walk
Authors	Rajesh Misra, Kumar S. Ray
Abstract	Particle swarm optimization comes under lot of changes after James Kennedy and Russell Eberhart first proposes the idea in 1995. The changes has been done mainly on Inertia parameters in velocity updating equation so that the convergence rate will be higher. We are proposing a novel approach where particles movement will not be depend on its velocity rather it will be decided by constrained biased random walk of particles. In random walk every particles movement based on two significant parameters, one is random process like toss of a coin and other is how much displacement a particle should have. In our approach we exploit this idea by performing a biased random operation and based on the outcome of that random operation, PSO particles choose the direction of the path and move non-uniformly into the solution space. This constrained, non-uniform movement helps the random walking particle to converge quicker then classical PSO. In our constrained biased random walking approach, we no longer needed velocity term (Vi), rather we introduce a new parameter (K) which is a probabilistic function. No global best particle (PGbest), local best particle (PLbest), Constriction parameter (W) are required rather we use a new term called Ptarg which is loosely influenced by PGbest.We test our algorithm on five different benchmark functions, and also compare its performance with classical PSO and Quantum Particle Swarm Optimization (QPSO).This new approach have been shown significantly better than basic PSO and sometime outperform QPSO in terms of convergence, search space, number of iterations.
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1711.10401v2
PDF	http://arxiv.org/pdf/1711.10401v2.pdf
PWC	https://paperswithcode.com/paper/a-modification-of-particle-swarm-optimization
Repo
Framework

Context-Independent Polyphonic Piano Onset Transcription with an Infinite Training Dataset


Title	Context-Independent Polyphonic Piano Onset Transcription with an Infinite Training Dataset
Authors	Samuel Li
Abstract	Many of the recent approaches to polyphonic piano note onset transcription require training a machine learning model on a large piano database. However, such approaches are limited by dataset availability; additional training data is difficult to produce, and proposed systems often perform poorly on novel recording conditions. We propose a method to quickly synthesize arbitrary quantities of training data, avoiding the need for curating large datasets. Various aspects of piano note dynamics - including nonlinearity of note signatures with velocity, different articulations, temporal clustering of onsets, and nonlinear note partial interference - are modeled to match the characteristics of real pianos. Our method also avoids the disentanglement problem, a recently noted issue affecting machine-learning based approaches. We train a feed-forward neural network with two hidden layers on our generated training data and achieve both good transcription performance on the large MAPS piano dataset and excellent generalization qualities.
Tasks
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08438v1
PDF	http://arxiv.org/pdf/1707.08438v1.pdf
PWC	https://paperswithcode.com/paper/context-independent-polyphonic-piano-onset
Repo
Framework

Stochastic Deep Learning in Memristive Networks


Title	Stochastic Deep Learning in Memristive Networks
Authors	Anakha V Babu, Bipin Rajendran
Abstract	We study the performance of stochastically trained deep neural networks (DNNs) whose synaptic weights are implemented using emerging memristive devices that exhibit limited dynamic range, resolution, and variability in their programming characteristics. We show that a key device parameter to optimize the learning efficiency of DNNs is the variability in its programming characteristics. DNNs with such memristive synapses, even with dynamic range as low as $15$ and only $32$ discrete levels, when trained based on stochastic updates suffer less than $3%$ loss in accuracy compared to floating point software baseline. We also study the performance of stochastic memristive DNNs when used as inference engines with noise corrupted data and find that if the device variability can be minimized, the relative degradation in performance for the Stochastic DNN is better than that of the software baseline. Hence, our study presents a new optimization corner for memristive devices for building large noise-immune deep learning systems.
Tasks
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03640v1
PDF	http://arxiv.org/pdf/1711.03640v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-deep-learning-in-memristive
Repo
Framework

On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests


Title	On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests
Authors	Krishnakumar Balasubramanian, Tong Li, Ming Yuan
Abstract	The reproducing kernel Hilbert space (RKHS) embedding of distributions offers a general and flexible framework for testing problems in arbitrary domains and has attracted considerable amount of attention in recent years. To gain insights into their operating characteristics, we study here the statistical performance of such approaches within a minimax framework. Focusing on the case of goodness-of-fit tests, our analyses show that a vanilla version of the kernel-embedding based test could be suboptimal, and suggest a simple remedy by moderating the embedding. We prove that the moderated approach provides optimal tests for a wide range of deviations from the null and can also be made adaptive over a large collection of interpolation spaces. Numerical experiments are presented to further demonstrate the merits of our approach.
Tasks
Published	2017-09-24
URL	http://arxiv.org/abs/1709.08148v1
PDF	http://arxiv.org/pdf/1709.08148v1.pdf
PWC	https://paperswithcode.com/paper/on-the-optimality-of-kernel-embedding-based
Repo
Framework

Video Processing for Barycenter Trajectory Identification in Diving


Title	Video Processing for Barycenter Trajectory Identification in Diving
Authors	Stefano Frassinelli, Alessandro Niccolai, Riccardo E. Zich
Abstract	The aim of this paper is to show a procedure for identify the barycentre of a diver by means of video processing. This procedure is aimed to introduce quantitative analysis tools and diving performance measurement and therefore in diving training. Sport performance analysis is a trend that is growing exponentially for all level athletes: it has been applied extensively in some sports such as cycling. Sport performance analysis has been applied mainly for high level athletes; in order to be used also for middle or low level athletes the proposed technique has to be flexible and low cost. Video processing is suitable to fulfil both these requirements. In diving, the first analysis that has to be done is the barycentre trajectory tracking.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02854v1
PDF	http://arxiv.org/pdf/1705.02854v1.pdf
PWC	https://paperswithcode.com/paper/video-processing-for-barycenter-trajectory
Repo
Framework

The Topology of Statistical Verifiability


Title	The Topology of Statistical Verifiability
Authors	Konstantin Genin, Kevin T. Kelly
Abstract	Topological models of empirical and formal inquiry are increasingly prevalent. They have emerged in such diverse fields as domain theory [1, 16], formal learning theory [18], epistemology and philosophy of science [10, 15, 8, 9, 2], statistics [6, 7] and modal logic [17, 4]. In those applications, open sets are typically interpreted as hypotheses deductively verifiable by true propositional information that rules out relevant possibilities. However, in statistical data analysis, one routinely receives random samples logically compatible with every statistical hypothesis. We bridge the gap between propositional and statistical data by solving for the unique topology on probability measures in which the open sets are exactly the statistically verifiable hypotheses. Furthermore, we extend that result to a topological characterization of learnability in the limit from statistical data.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1707.09378v1
PDF	http://arxiv.org/pdf/1707.09378v1.pdf
PWC	https://paperswithcode.com/paper/the-topology-of-statistical-verifiability
Repo
Framework

Deep Learning for Logo Recognition


Title	Deep Learning for Logo Recognition
Authors	Simone Bianco, Marco Buzzelli, Davide Mazzini, Raimondo Schettini
Abstract	In this paper we propose a method for logo recognition using deep learning. Our recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network (CNN) specifically trained for logo classification, even if they are not precisely localized. Experiments are carried out on the FlickrLogos-32 database, and we evaluate the effect on recognition performance of synthetic versus real data augmentation, and image pre-processing. Moreover, we systematically investigate the benefits of different training choices such as class-balancing, sample-weighting and explicit modeling the background class (i.e. no-logo regions). Experimental results confirm the feasibility of the proposed method, that outperforms the methods in the state of the art.
Tasks	Data Augmentation, Logo Recognition
Published	2017-01-10
URL	http://arxiv.org/abs/1701.02620v2
PDF	http://arxiv.org/pdf/1701.02620v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-logo-recognition
Repo
Framework

Learning by Asking Questions


Title	Learning by Asking Questions
Authors	Ishan Misra, Ross Girshick, Rob Fergus, Martial Hebert, Abhinav Gupta, Laurens van der Maaten
Abstract	We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task. LBA differs from standard VQA training in that most questions are not observed during training time, and the learner must ask questions it wants answers to. Thus, LBA more closely mimics natural learning and has the potential to be more data-efficient than the traditional VQA setting. We present a model that performs LBA on the CLEVR dataset, and show that it automatically discovers an easy-to-hard curriculum when learning interactively from an oracle. Our LBA generated data consistently matches or outperforms the CLEVR train data and is more sample efficient. We also show that our model asks questions that generalize to state-of-the-art VQA models and to novel test time distributions.
Tasks	Question Answering, Visual Question Answering
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01238v1
PDF	http://arxiv.org/pdf/1712.01238v1.pdf
PWC	https://paperswithcode.com/paper/learning-by-asking-questions
Repo
Framework

Data Noising as Smoothing in Neural Network Language Models


Title	Data Noising as Smoothing in Neural Network Language Models
Authors	Ziang Xie, Sida I. Wang, Jiwei Li, Daniel Lévy, Aiming Nie, Dan Jurafsky, Andrew Y. Ng
Abstract	Data noising is an effective technique for regularizing neural network models. While noising is widely adopted in application domains such as vision and speech, commonly used noising primitives have not been developed for discrete sequence-level settings such as language modeling. In this paper, we derive a connection between input noising in neural network language models and smoothing in $n$-gram models. Using this connection, we draw upon ideas from smoothing to develop effective noising schemes. We demonstrate performance gains when applying the proposed schemes to language modeling and machine translation. Finally, we provide empirical analysis validating the relationship between noising and smoothing.
Tasks	Language Modelling, Machine Translation
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02573v1
PDF	http://arxiv.org/pdf/1703.02573v1.pdf
PWC	https://paperswithcode.com/paper/data-noising-as-smoothing-in-neural-network
Repo
Framework

SeDAR - Semantic Detection and Ranging: Humans can localise without LiDAR, can robots?


Title	SeDAR - Semantic Detection and Ranging: Humans can localise without LiDAR, can robots?
Authors	Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden
Abstract	How does a person work out their location using a floorplan? It is probably safe to say that we do not explicitly measure depths to every visible surface and try to match them against different pose estimates in the floorplan. And yet, this is exactly how most robotic scan-matching algorithms operate. Similarly, we do not extrude the 2D geometry present in the floorplan into 3D and try to align it to the real-world. And yet, this is how most vision-based approaches localise. Humans do the exact opposite. Instead of depth, we use high level semantic cues. Instead of extruding the floorplan up into the third dimension, we collapse the 3D world into a 2D representation. Evidence of this is that many of the floorplans we use in everyday life are not accurate, opting instead for high levels of discriminative landmarks. In this work, we use this insight to present a global localisation approach that relies solely on the semantic labels present in the floorplan and extracted from RGB images. While our approach is able to use range measurements if available, we demonstrate that they are unnecessary as we can achieve results comparable to state-of-the-art without them.
Tasks
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01500v2
PDF	http://arxiv.org/pdf/1709.01500v2.pdf
PWC	https://paperswithcode.com/paper/sedar-semantic-detection-and-ranging-humans
Repo
Framework

Wages of wins: could an amateur make money from match outcome predictions?


Title	Wages of wins: could an amateur make money from match outcome predictions?
Authors	Albrecht Zimmermann
Abstract	Evaluating the accuracies of models for match outcome predictions is nice and well but in the end the real proof is in the money to be made by betting. To evaluate the question whether the models developed by us could be used easily to make money via sports betting, we evaluate three cases: NCAAB post-season, NBA season, and NFL season, and find that it is possible yet not without its pitfalls. In particular, we illustrate that high accuracy does not automatically equal high pay-out, by looking at the type of match-ups that are predicted correctly by different models.
Tasks
Published	2017-02-17
URL	http://arxiv.org/abs/1702.05982v1
PDF	http://arxiv.org/pdf/1702.05982v1.pdf
PWC	https://paperswithcode.com/paper/wages-of-wins-could-an-amateur-make-money
Repo
Framework