October 17, 2019

2920 words 14 mins read

Paper Group ANR 971

3D Registration of Curves and Surfaces using Local Differential Information. A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes. Deep Compression of Sum-Product Networks on Tensor Networks. On the Perceptron’s Compression. Adaptive Stress Testing: Finding Failure Events with Reinforc …

3D Registration of Curves and Surfaces using Local Differential Information


Title	3D Registration of Curves and Surfaces using Local Differential Information
Authors	Carolina Raposo, Joao P. Barreto
Abstract	This article presents for the first time a global method for registering 3D curves with 3D surfaces without requiring an initialization. The algorithm works with 2-tuples point+vector that consist in pairs of points augmented with the information of their tangents or normals. A closed-form solution for determining the alignment transformation from a pair of matching 2-tuples is proposed. In addition, the set of necessary conditions for two 2-tuples to match is derived. This allows fast search of correspondences that are used in an hypothesise-and-test framework for accomplishing global registration. Comparative experiments demonstrate that the proposed algorithm is the first effective solution for curve vs surface registration, with the method achieving accurate alignment in situations of small overlap and large percentage of outliers in a fraction of a second. The proposed framework is extended to the cases of curve vs curve and surface vs surface registration, with the former being particularly relevant since it is also a largely unsolved problem.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00637v1
PDF	http://arxiv.org/pdf/1804.00637v1.pdf
PWC	https://paperswithcode.com/paper/3d-registration-of-curves-and-surfaces-using
Repo
Framework

A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes


Title	A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes
Authors	Ahmad Khaliq, Shoaib Ehsan, Zetao Chen, Michael Milford, Klaus McDonald-Maier
Abstract	This paper presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12x average speedup relative to state-of-the-art methods.
Tasks	Visual Place Recognition
Published	2018-11-07
URL	https://arxiv.org/abs/1811.03032v4
PDF	https://arxiv.org/pdf/1811.03032v4.pdf
PWC	https://paperswithcode.com/paper/a-holistic-visual-place-recognition-approach
Repo
Framework

Deep Compression of Sum-Product Networks on Tensor Networks


Title	Deep Compression of Sum-Product Networks on Tensor Networks
Authors	Ching-Yun Ko, Cong Chen, Yuke Zhang, Kim Batselier, Ngai Wong
Abstract	Sum-product networks (SPNs) represent an emerging class of neural networks with clear probabilistic semantics and superior inference speed over graphical models. This work reveals a strikingly intimate connection between SPNs and tensor networks, thus leading to a highly efficient representation that we call tensor SPNs (tSPNs). For the first time, through mapping an SPN onto a tSPN and employing novel optimization techniques, we demonstrate remarkable parameter compression with negligible loss in accuracy.
Tasks	Tensor Networks
Published	2018-11-09
URL	http://arxiv.org/abs/1811.03963v1
PDF	http://arxiv.org/pdf/1811.03963v1.pdf
PWC	https://paperswithcode.com/paper/deep-compression-of-sum-product-networks-on
Repo
Framework

On the Perceptron’s Compression


Title	On the Perceptron’s Compression
Authors	Shay Moran, Ido Nachum, Itai Panasoff, Amir Yehudayoff
Abstract	We study and provide exposition to several phenomena that are related to the perceptron’s compression. One theme concerns modifications of the perceptron algorithm that yield better guarantees on the margin of the hyperplane it outputs. These modifications can be useful in training neural networks as well, and we demonstrate them with some experimental data. In a second theme, we deduce conclusions from the perceptron’s compression in various contexts.
Tasks
Published	2018-06-14
URL	http://arxiv.org/abs/1806.05403v1
PDF	http://arxiv.org/pdf/1806.05403v1.pdf
PWC	https://paperswithcode.com/paper/on-the-perceptrons-compression
Repo
Framework

Adaptive Stress Testing: Finding Failure Events with Reinforcement Learning


Title	Adaptive Stress Testing: Finding Failure Events with Reinforcement Learning
Authors	Ritchie Lee, Ole J. Mengshoel, Anshu Saksena, Ryan Gardner, Daniel Genin, Joshua Silbermann, Michael Owen, Mykel J. Kochenderfer
Abstract	Finding the most likely path to a set of failure states is important to the analysis of safety-critical dynamic systems. While efficient solutions exist for certain classes of systems, a scalable general solution for stochastic, partially-observable, and continuous-valued systems remains challenging. Existing approaches in formal and simulation-based methods either cannot scale to large systems or are computationally inefficient. This paper presents adaptive stress testing (AST), a framework for searching a simulator for the most likely path to a failure event. We formulate the problem as a Markov decision process and use reinforcement learning to optimize it. The approach is simulation-based and does not require internal knowledge of the system. As a result, the approach is very suitable for black box testing of large systems. We present formulations for both systems where the state is fully-observable and partially-observable. In the latter case, we present a modified Monte Carlo tree search algorithm that only requires access to the pseudorandom number generator of the simulator to overcome partial observability. We also present an extension of the framework, called differential adaptive stress testing (DAST), that can be used to find failures that occur in one system but not in another. This type of differential analysis is useful in applications such as regression testing, where one is concerned with finding areas of relative weakness compared to a baseline. We demonstrate the effectiveness of the approach on an aircraft collision avoidance application, where we stress test a prototype aircraft collision avoidance system to find high-probability scenarios of near mid-air collisions.
Tasks
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02188v1
PDF	http://arxiv.org/pdf/1811.02188v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-stress-testing-finding-failure
Repo
Framework

Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties


Title	Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
Authors	Michael Eickenberg, Georgios Exarchakis, Matthew Hirn, Stéphane Mallat, Louis Thiry
Abstract	We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory. Using Gaussian-type orbital functions, we create surrogate electronic densities of the molecule from which we compute invariant “solid harmonic scattering coefficients” that account for different types of interactions at different scales. Multi-linear regressions of various physical properties of molecules are computed from these invariant coefficients. Numerical experiments show that these regressions have near state of the art performance, even with relatively few training examples. Predictions over small sets of scattering coefficients can reach a DFT precision while being interpretable.
Tasks
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00571v1
PDF	http://arxiv.org/pdf/1805.00571v1.pdf
PWC	https://paperswithcode.com/paper/solid-harmonic-wavelet-scattering-for
Repo
Framework

Bayesian Spectral Deconvolution Based on Poisson Distribution: Bayesian Measurement and Virtual Measurement Analytics (VMA)


Title	Bayesian Spectral Deconvolution Based on Poisson Distribution: Bayesian Measurement and Virtual Measurement Analytics (VMA)
Authors	Kenji Nagata, Yoh-ichi Mototake, Rei Muraoka, Takehiko Sasaki, Masato Okada
Abstract	In this paper, we propose a new method of Bayesian measurement for spectral deconvolution, which regresses spectral data into the sum of unimodal basis function such as Gaussian or Lorentzian functions. Bayesian measurement is a framework for considering not only the target physical model but also the measurement model as a probabilistic model, and enables us to estimate the parameter of a physical model with its confidence interval through a Bayesian posterior distribution given a measurement data set. The measurement with Poisson noise is one of the most effective system to apply our proposed method. Since the measurement time is strongly related to the signal-to-noise ratio for the Poisson noise model, Bayesian measurement with Poisson noise model enables us to clarify the relationship between the measurement time and the limit of estimation. In this study, we establish the probabilistic model with Poisson noise for spectral deconvolution. Bayesian measurement enables us to perform virtual and computer simulation for a certain measurement through the established probabilistic model. This property is called “Virtual Measurement Analytics(VMA)” in this paper. We also show that the relationship between the measurement time and the limit of estimation can be extracted by using the proposed method in a simulation of synthetic data and real data for XPS measurement of MoS$_2$.
Tasks
Published	2018-12-11
URL	http://arxiv.org/abs/1812.05501v1
PDF	http://arxiv.org/pdf/1812.05501v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-spectral-deconvolution-based-on
Repo
Framework

Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems


Title	Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
Authors	Svetlana Kiritchenko, Saif M. Mohammad
Abstract	Automatic machine learning systems can inadvertently accentuate and perpetuate inappropriate human biases. Past work on examining inappropriate biases has largely focused on just individual systems. Further, there is no benchmark dataset for examining inappropriate biases in systems. Here for the first time, we present the Equity Evaluation Corpus (EEC), which consists of 8,640 English sentences carefully chosen to tease out biases towards certain races and genders. We use the dataset to examine 219 automatic sentiment analysis systems that took part in a recent shared task, SemEval-2018 Task 1 ‘Affect in Tweets’. We find that several of the systems show statistically significant bias; that is, they consistently provide slightly higher sentiment intensity predictions for one race or one gender. We make the EEC freely available.
Tasks	Sentiment Analysis
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04508v1
PDF	http://arxiv.org/pdf/1805.04508v1.pdf
PWC	https://paperswithcode.com/paper/examining-gender-and-race-bias-in-two-hundred
Repo
Framework

Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice


Title	Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice
Authors	Yan Deng, Lei He, Frank Soong
Abstract	Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or enhancing a premium voice by utilizing the data from other speakers for richer contextual coverage and better generalization. A multi-speaker neural TTS model is built with the embedded speaker information in both spectral and speaker latent space. The experimental results show that, with less than 5 minutes of training data from a new speaker, the new model can achieve an MOS score of 4.16 in naturalness and 4.64 in speaker similarity close to human recordings (4.74). For a well-trained premium voice, we can achieve an MOS score of 4.5 for out-of-domain texts, which is comparable to an MOS of 4.58 for professional recordings, and significantly outperforms single speaker result of 4.28.
Tasks
Published	2018-12-13
URL	https://arxiv.org/abs/1812.05253v4
PDF	https://arxiv.org/pdf/1812.05253v4.pdf
PWC	https://paperswithcode.com/paper/modeling-multi-speaker-latent-space-to
Repo
Framework

Rule-based OWL Modeling with ROWLTab Protege Plugin


Title	Rule-based OWL Modeling with ROWLTab Protege Plugin
Authors	Md. Kamruzzaman Sarker, Adila Krisnadhi, David Carral, Pascal Hitzler
Abstract	It has been argued that it is much easier to convey logical statements using rules rather than OWL (or description logic (DL)) axioms. Based on recent theoretical developments on transformations between rules and DLs, we have developed ROWLTab, a Protege plugin that allows users to enter OWL axioms by way of rules; the plugin then automatically converts these rules into OWL 2 DL axioms if possible, and prompts the user in case such a conversion is not possible without weakening the semantics of the rule. In this paper, we present ROWLTab, together with a user evaluation of its effectiveness compared to entering axioms using the standard Protege interface. Our evaluation shows that modeling with ROWLTab is much quicker than the standard interface, while at the same time, also less prone to errors for hard modeling tasks.
Tasks
Published	2018-08-30
URL	http://arxiv.org/abs/1808.10108v1
PDF	http://arxiv.org/pdf/1808.10108v1.pdf
PWC	https://paperswithcode.com/paper/rule-based-owl-modeling-with-rowltab-protege
Repo
Framework

Minnorm training: an algorithm for training over-parameterized deep neural networks


Title	Minnorm training: an algorithm for training over-parameterized deep neural networks
Authors	Yamini Bansal, Madhu Advani, David D Cox, Andrew M Saxe
Abstract	In this work, we propose a new training method for finding minimum weight norm solutions in over-parameterized neural networks (NNs). This method seeks to improve training speed and generalization performance by framing NN training as a constrained optimization problem wherein the sum of the norm of the weights in each layer of the network is minimized, under the constraint of exactly fitting training data. It draws inspiration from support vector machines (SVMs), which are able to generalize well, despite often having an infinite number of free parameters in their primal form, and from recent theoretical generalization bounds on NNs which suggest that lower norm solutions generalize better. To solve this constrained optimization problem, our method employs Lagrange multipliers that act as integrators of error over training and identify `support vector’-like examples. The method can be implemented as a wrapper around gradient based methods and uses standard back-propagation of gradients from the NN for both regression and classification versions of the algorithm. We provide theoretical justifications for the effectiveness of this algorithm in comparison to early stopping and $L_2$-regularization using simple, analytically tractable settings. In particular, we show faster convergence to the max-margin hyperplane in a shallow network (compared to vanilla gradient descent); faster convergence to the minimum-norm solution in a linear chain (compared to $L_2$-regularization); and initialization-independent generalization performance in a deep linear network. Finally, using the MNIST dataset, we demonstrate that this algorithm can boost test accuracy and identify difficult examples in real-world datasets. \|
Tasks
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00730v2
PDF	http://arxiv.org/pdf/1806.00730v2.pdf
PWC	https://paperswithcode.com/paper/minnorm-training-an-algorithm-for-training
Repo
Framework

On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions


Title	On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
Authors	Yusuke Tsuzuku, Issei Sato
Abstract	Data-agnostic quasi-imperceptible perturbations on inputs are known to degrade recognition accuracy of deep convolutional networks severely. This phenomenon is considered to be a potential security issue. Moreover, some results on statistical generalization guarantees indicate that the phenomenon can be a key to improve the networks’ generalization. However, the characteristics of the shared directions of such harmful perturbations remain unknown. Our primal finding is that convolutional networks are sensitive to the directions of Fourier basis functions. We derived the property by specializing a hypothesis of the cause of the sensitivity, known as the linearity of neural networks, to convolutional networks and empirically validated it. As a by-product of the analysis, we propose an algorithm to create shift-invariant universal adversarial perturbations available in black-box settings.
Tasks
Published	2018-09-11
URL	http://arxiv.org/abs/1809.04098v2
PDF	http://arxiv.org/pdf/1809.04098v2.pdf
PWC	https://paperswithcode.com/paper/on-the-structural-sensitivity-of-deep
Repo
Framework

Matching Fingerphotos to Slap Fingerprint Images


Title	Matching Fingerphotos to Slap Fingerprint Images
Authors	Debayan Deb, Tarang Chugh, Joshua Engelsma, Kai Cao, Neeta Nain, Jake Kendall, Anil K. Jain
Abstract	We address the problem of comparing fingerphotos, fingerprint images from a commodity smartphone camera, with the corresponding legacy slap contact-based fingerprint images. Development of robust versions of these technologies would enable the use of the billions of standard Android phones as biometric readers through a simple software download, dramatically lowering the cost and complexity of deployment relative to using a separate fingerprint reader. Two fingerphoto apps running on Android phones and an optical slap reader were utilized for fingerprint collection of 309 subjects who primarily work as construction workers, farmers, and domestic helpers. Experimental results show that a True Accept Rate (TAR) of 95.79 at a False Accept Rate (FAR) of 0.1% can be achieved in matching fingerphotos to slaps (two thumbs and two index fingers) using a COTS fingerprint matcher. By comparison, a baseline TAR of 98.55% at 0.1% FAR is achieved when matching fingerprint images from two different contact-based optical readers. We also report the usability of the two smartphone apps, in terms of failure to acquire rate and fingerprint acquisition time. Our results show that fingerphotos are promising to authenticate individuals (against a national ID database) for banking, welfare distribution, and healthcare applications in developing countries.
Tasks
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08122v1
PDF	http://arxiv.org/pdf/1804.08122v1.pdf
PWC	https://paperswithcode.com/paper/matching-fingerphotos-to-slap-fingerprint
Repo
Framework

Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches


Title	Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches
Authors	Simon Olofsson, Marc Peter Deisenroth, Ruth Misener
Abstract	Healthcare companies must submit pharmaceutical drugs or medical devices to regulatory bodies before marketing new technology. Regulatory bodies frequently require transparent and interpretable computational modelling to justify a new healthcare technology, but researchers may have several competing models for a biological system and too little data to discriminate between the models. In design of experiments for model discrimination, the goal is to design maximally informative physical experiments in order to discriminate between rival predictive models. Prior work has focused either on analytical approaches, which cannot manage all functions, or on data-driven approaches, which may have computational difficulties or lack interpretable marginal predictive distributions. We develop a methodology introducing Gaussian process surrogates in lieu of the original mechanistic models. We thereby extend existing design and model discrimination methods developed for analytical models to cases of non-analytical models in a computationally efficient manner.
Tasks
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04170v2
PDF	http://arxiv.org/pdf/1802.04170v2.pdf
PWC	https://paperswithcode.com/paper/design-of-experiments-for-model
Repo
Framework

InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation


Title	InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation
Authors	Shubham Kumar, Sailesh Conjeti, Abhijit Guha Roy, Christian Wachinger, Nassir Navab
Abstract	We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended for other segmentation tasks involving multi-modalities. InfiNet consists of double encoder arms for T1 and T2 input scans that feed into a joint-decoder arm that terminates in the classification layer. The novelty of InfiNet lies in the manner in which the decoder upsamples lower resolution input feature map(s) from multiple encoder arms. Specifically, the pooled indices computed in the max-pooling layers of each of the encoder blocks are related to the corresponding decoder block to perform non-linear learning-free upsampling. The sparse maps are concatenated with intermediate encoder representations (skip connections) and convolved with trainable filters to produce dense feature maps. InfiNet is trained end-to-end to optimize for the Generalized Dice Loss, which is well-suited for high class imbalance. InfiNet achieves the whole-volume segmentation in under 50 seconds and we demonstrate competitive performance against multiple state-of-the art deep architectures and their multi-modal variants.
Tasks	Infant Brain Mri Segmentation, Semantic Segmentation
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05735v1
PDF	http://arxiv.org/pdf/1810.05735v1.pdf
PWC	https://paperswithcode.com/paper/infinet-fully-convolutional-networks-for
Repo
Framework