October 19, 2019

3004 words 15 mins read

Paper Group ANR 175

Paper Group ANR 175

Semi-supervised Feature Learning For Improving Writer Identification. A Bayesian Approach to Income Inference in a Communication Network. Language Expansion In Text-Based Games. LiDAR and Camera Calibration using Motion Estimated by Sensor Fusion Odometry. An improvement of the convergence proof of the ADAM-Optimizer. Few-Shot Learning with Metric- …

Semi-supervised Feature Learning For Improving Writer Identification

Title Semi-supervised Feature Learning For Improving Writer Identification
Authors Shiming Chen, Yisong Wang, Chin-Teng Lin, Weiping Ding, Zehong Cao
Abstract Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors. In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification by training with extra unlabeled data and the original labeled data simultaneously. Specifically, we proposed a weighted label smoothing regularization (WLSR) method for data augmentation, which assigned the weighted uniform label distribution to the extra unlabeled data. The WLSR method could regularize the convolutional neural network (CNN) baseline to allow more discriminative features to be learned to represent the properties of different writing styles. The experimental results on well-known benchmark datasets (ICDAR2013 and CVL) showed that our proposed semi-supervised feature learning approach could significantly improve the baseline measurement and perform competitively with existing writer identification approaches. Our findings provide new insights into offline write identification.
Tasks Data Augmentation
Published 2018-07-15
URL http://arxiv.org/abs/1807.05490v3
PDF http://arxiv.org/pdf/1807.05490v3.pdf
PWC https://paperswithcode.com/paper/semi-supervised-feature-learning-for
Repo
Framework

A Bayesian Approach to Income Inference in a Communication Network

Title A Bayesian Approach to Income Inference in a Communication Network
Authors Martin Fixman, Ariel Berenstein, Jorge Brea, Martin Minnoni, Matias Travizano, Carlos Sarraute
Abstract The explosion of mobile phone communications in the last years occurs at a moment where data processing power increases exponentially. Thanks to those two changes in a global scale, the road has been opened to use mobile phone communications to generate inferences and characterizations of mobile phone users. In this work, we use the communication network, enriched by a set of users’ attributes, to gain a better understanding of the demographic features of a population. Namely, we use call detail records and banking information to infer the income of each person in the graph.
Tasks
Published 2018-11-10
URL http://arxiv.org/abs/1811.04246v1
PDF http://arxiv.org/pdf/1811.04246v1.pdf
PWC https://paperswithcode.com/paper/a-bayesian-approach-to-income-inference-in-a
Repo
Framework

Language Expansion In Text-Based Games

Title Language Expansion In Text-Based Games
Authors Ghulam Ahmed Ansari, Sagar J P, Sarath Chandar, Balaraman Ravindran
Abstract Text-based games are suitable test-beds for designing agents that can learn by interaction with the environment in the form of natural language text. Very recently, deep reinforcement learning based agents have been successfully applied for playing text-based games. In this paper, we explore the possibility of designing a single agent to play several text-based games and of expanding the agent’s vocabulary using the vocabulary of agents trained for multiple games. To this extent, we explore the application of recently proposed policy distillation method for video games to the text-based game setting. We also use text-based games as a test-bed to analyze and hence understand policy distillation approach in detail.
Tasks
Published 2018-05-17
URL http://arxiv.org/abs/1805.07274v1
PDF http://arxiv.org/pdf/1805.07274v1.pdf
PWC https://paperswithcode.com/paper/language-expansion-in-text-based-games
Repo
Framework

LiDAR and Camera Calibration using Motion Estimated by Sensor Fusion Odometry

Title LiDAR and Camera Calibration using Motion Estimated by Sensor Fusion Odometry
Authors Ryoichi Ishikawa, Takeshi Oishi, Katsushi Ikeuchi
Abstract In this paper, we propose a method of targetless and automatic Camera-LiDAR calibration. Our approach is an extension of hand-eye calibration framework to 2D-3D calibration. By using the sensor fusion odometry method, the scaled camera motions are calculated with high accuracy. In addition to this, we clarify the suitable motion for this calibration method. The proposed method only requires the three-dimensional point cloud and the camera image and does not need other information such as reflectance of LiDAR and to give initial extrinsic parameter. In the experiments, we demonstrate our method using several sensor configurations in indoor and outdoor scenes to verify the effectiveness. The accuracy of our method achieves more than other comparable state-of-the-art methods.
Tasks Calibration, Sensor Fusion
Published 2018-04-14
URL http://arxiv.org/abs/1804.05178v1
PDF http://arxiv.org/pdf/1804.05178v1.pdf
PWC https://paperswithcode.com/paper/lidar-and-camera-calibration-using-motion
Repo
Framework

An improvement of the convergence proof of the ADAM-Optimizer

Title An improvement of the convergence proof of the ADAM-Optimizer
Authors Sebastian Bock, Josef Goppold, Martin Weiß
Abstract A common way to train neural networks is the Backpropagation. This algorithm includes a gradient descent method, which needs an adaptive step size. In the area of neural networks, the ADAM-Optimizer is one of the most popular adaptive step size methods. It was invented in \cite{Kingma.2015} by Kingma and Ba. The $5865$ citations in only three years shows additionally the importance of the given paper. We discovered that the given convergence proof of the optimizer contains some mistakes, so that the proof will be wrong. In this paper we give an improvement to the convergence proof of the ADAM-Optimizer.
Tasks
Published 2018-04-27
URL http://arxiv.org/abs/1804.10587v1
PDF http://arxiv.org/pdf/1804.10587v1.pdf
PWC https://paperswithcode.com/paper/an-improvement-of-the-convergence-proof-of
Repo
Framework

Few-Shot Learning with Metric-Agnostic Conditional Embeddings

Title Few-Shot Learning with Metric-Agnostic Conditional Embeddings
Authors Nathan Hilliard, Lawrence Phillips, Scott Howland, Artëm Yankov, Courtney D. Corley, Nathan O. Hodas
Abstract Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison. This allows the network to decide what aspects of each class are important for the comparison at hand. We find that this flexible architecture works well in practice, achieving state-of-the-art performance on the Caltech-UCSD birds fine-grained classification task.
Tasks Few-Shot Learning, Metric Learning
Published 2018-02-12
URL http://arxiv.org/abs/1802.04376v1
PDF http://arxiv.org/pdf/1802.04376v1.pdf
PWC https://paperswithcode.com/paper/few-shot-learning-with-metric-agnostic
Repo
Framework

Probabilistic Model Checking of Robots Deployed in Extreme Environments

Title Probabilistic Model Checking of Robots Deployed in Extreme Environments
Authors Xingyu Zhao, Valentin Robu, David Flynn, Fateme Dinmohammadi, Michael Fisher, Matt Webster
Abstract Robots are increasingly used to carry out critical missions in extreme environments that are hazardous for humans. This requires a high degree of operational autonomy under uncertain conditions, and poses new challenges for assuring the robot’s safety and reliability. In this paper, we develop a framework for probabilistic model checking on a layered Markov model to verify the safety and reliability requirements of such robots, both at pre-mission stage and during runtime. Two novel estimators based on conservative Bayesian inference and imprecise probability model with sets of priors are introduced to learn the unknown transition parameters from operational data. We demonstrate our approach using data from a real-world deployment of unmanned underwater vehicles in extreme environments.
Tasks Bayesian Inference
Published 2018-12-10
URL http://arxiv.org/abs/1812.04128v3
PDF http://arxiv.org/pdf/1812.04128v3.pdf
PWC https://paperswithcode.com/paper/probabilistic-model-checking-of-robots
Repo
Framework

Deep Pose Consensus Networks

Title Deep Pose Consensus Networks
Authors Geonho Cha, Minsik Lee, Jungchan Cho, Songhwai Oh
Abstract In this paper, we address the problem of estimating a 3D human pose from a single image, which is important but difficult to solve due to many reasons, such as self-occlusions, wild appearance changes, and inherent ambiguities of 3D estimation from a 2D cue. These difficulties make the problem ill-posed, which have become requiring increasingly complex estimators to enhance the performance. On the other hand, most existing methods try to handle this problem based on a single complex estimator, which might not be good solutions. In this paper, to resolve this issue, we propose a multiple-partial-hypothesis-based framework for the problem of estimating 3D human pose from a single image, which can be fine-tuned in an end-to-end fashion. We first select several joint groups from a human joint model using the proposed sampling scheme, and estimate the 3D poses of each joint group separately based on deep neural networks. After that, they are aggregated to obtain the final 3D poses using the proposed robust optimization formula. The overall procedure can be fine-tuned in an end-to-end fashion, resulting in better performance. In the experiments, the proposed framework shows the state-of-the-art performances on popular benchmark data sets, namely Human3.6M and HumanEva, which demonstrate the effectiveness of the proposed framework.
Tasks
Published 2018-03-22
URL https://arxiv.org/abs/1803.08190v2
PDF https://arxiv.org/pdf/1803.08190v2.pdf
PWC https://paperswithcode.com/paper/deep-pose-consensus-networks
Repo
Framework

A human-editable Sign Language representation for software editing—and a writing system?

Title A human-editable Sign Language representation for software editing—and a writing system?
Authors Michael Filhol
Abstract To equip SL with software properly, we need an input system to represent and manipulate signed contents in the same way that every day software allows to process written text. Refuting the claim that video is good enough a medium to serve the purpose, we propose to build a representation that is: editable, queryable, synthesisable and user-friendly—we define those terms upfront. The issue being functionally and conceptually linked to that of writing, we study existing writing systems, namely those in use for vocal languages, those designed and proposed for SLs, and more spontaneous ways in which SL users put their language in writing. Observing each paradigm in turn, we move on to propose a new approach to satisfy our goals of integration in software. We finally open the prospect of our proposition being used outside of this restricted scope, as a writing system in itself, and compare its properties to the other writing systems presented.
Tasks
Published 2018-11-05
URL http://arxiv.org/abs/1811.01786v1
PDF http://arxiv.org/pdf/1811.01786v1.pdf
PWC https://paperswithcode.com/paper/a-human-editable-sign-language-representation
Repo
Framework

Cortex Neural Network: learning with Neural Network groups

Title Cortex Neural Network: learning with Neural Network groups
Authors Liyao Gao
Abstract Neural Network has been successfully applied to many real-world problems, such as image recognition and machine translation. However, for the current architecture of neural networks, it is hard to perform complex cognitive tasks, for example, to process the image and audio inputs together. Cortex, as an important architecture in the brain, is important for animals to perform the complex cognitive task. We view the architecture of Cortex in the brain as a missing part in the design of the current artificial neural network. In this paper, we purpose Cortex Neural Network (CrtxNN). The Cortex Neural Network is an upper architecture of neural networks which motivated from cerebral cortex in the brain to handle different tasks in the same learning system. It is able to identify different tasks and solve them with different methods. In our implementation, the Cortex Neural Network is able to process different cognitive tasks and perform reflection to get a higher accuracy. We provide a series of experiments to examine the capability of the cortex architecture on traditional neural networks. Our experiments proved its ability on the Cortex Neural Network can reach accuracy by 98.32% on MNIST and 62% on CIFAR10 at the same time, which can promisingly reduce the loss by 40%.
Tasks Machine Translation
Published 2018-04-10
URL http://arxiv.org/abs/1804.03313v1
PDF http://arxiv.org/pdf/1804.03313v1.pdf
PWC https://paperswithcode.com/paper/cortex-neural-network-learning-with-neural
Repo
Framework

Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models

Title Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
Authors Jiawei Zhang, Yang Wang, Piero Molino, Lezhi Li, David S. Ebert
Abstract Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation, debugging, and comparison of machine learning models in a more transparent and interactive manner. Conventional techniques usually focus on visualizing the internal logic of a specific model type (i.e., deep neural networks), lacking the ability to extend to a more complex scenario where different model types are integrated. To this end, Manifold is designed as a generic framework that does not rely on or access the internal logic of the model and solely observes the input (i.e., instances or features) and the output (i.e., the predicted result and probability distribution). We describe the workflow of Manifold as an iterative process consisting of three major phases that are commonly involved in the model development and diagnosis process: inspection (hypothesis), explanation (reasoning), and refinement (verification). The visual components supporting these tasks include a scatterplot-based visual summary that overviews the models’ outcome and a customizable tabular view that reveals feature discrimination. We demonstrate current applications of the framework on the classification and regression tasks and discuss other potential machine learning use scenarios where Manifold can be applied.
Tasks
Published 2018-08-01
URL http://arxiv.org/abs/1808.00196v1
PDF http://arxiv.org/pdf/1808.00196v1.pdf
PWC https://paperswithcode.com/paper/manifold-a-model-agnostic-framework-for
Repo
Framework

Behavioral Learning of Aircraft Landing Sequencing Using a Society of Probabilistic Finite State Machines

Title Behavioral Learning of Aircraft Landing Sequencing Using a Society of Probabilistic Finite State Machines
Authors Jiangjun Tang, Hussein A. Abbass
Abstract Air Traffic Control (ATC) is a complex safety critical environment. A tower controller would be making many decisions in real-time to sequence aircraft. While some optimization tools exist to help the controller in some airports, even in these situations, the real sequence of the aircraft adopted by the controller is significantly different from the one proposed by the optimization algorithm. This is due to the very dynamic nature of the environment. The objective of this paper is to test the hypothesis that one can learn from the sequence adopted by the controller some strategies that can act as heuristics in decision support tools for aircraft sequencing. This aim is tested in this paper by attempting to learn sequences generated from a well-known sequencing method that is being used in the real world. The approach relies on a genetic algorithm (GA) to learn these sequences using a society Probabilistic Finite-state Machines (PFSMs). Each PFSM learns a different sub-space; thus, decomposing the learning problem into a group of agents that need to work together to learn the overall problem. Three sequence metrics (Levenshtein, Hamming and Position distances) are compared as the fitness functions in GA. As the results suggest, it is possible to learn the behavior of the algorithm/heuristic that generated the original sequence from very limited information.
Tasks
Published 2018-02-27
URL http://arxiv.org/abs/1802.10203v1
PDF http://arxiv.org/pdf/1802.10203v1.pdf
PWC https://paperswithcode.com/paper/behavioral-learning-of-aircraft-landing
Repo
Framework

Automatic Grammar Augmentation for Robust Voice Command Recognition

Title Automatic Grammar Augmentation for Robust Voice Command Recognition
Authors Yang Yang, Anusha Lalitha, Jinwon Lee, Chris Lott
Abstract This paper proposes a novel pipeline for automatic grammar augmentation that provides a significant improvement in the voice command recognition accuracy for systems with small footprint acoustic model (AM). The improvement is achieved by augmenting the user-defined voice command set, also called grammar set, with alternate grammar expressions. For a given grammar set, a set of potential grammar expressions (candidate set) for augmentation is constructed from an AM-specific statistical pronunciation dictionary that captures the consistent patterns and errors in the decoding of AM induced by variations in pronunciation, pitch, tempo, accent, ambiguous spellings, and noise conditions. Using this candidate set, greedy optimization based and cross-entropy-method (CEM) based algorithms are considered to search for an augmented grammar set with improved recognition accuracy utilizing a command-specific dataset. Our experiments show that the proposed pipeline along with algorithms considered in this paper significantly reduce the mis-detection and mis-classification rate without increasing the false-alarm rate. Experiments also demonstrate the consistent superior performance of CEM method over greedy-based algorithms.
Tasks
Published 2018-11-14
URL http://arxiv.org/abs/1811.06096v1
PDF http://arxiv.org/pdf/1811.06096v1.pdf
PWC https://paperswithcode.com/paper/automatic-grammar-augmentation-for-robust
Repo
Framework

Reasoning From Data in the Mathematical Theory of Evidence

Title Reasoning From Data in the Mathematical Theory of Evidence
Authors Mieczysław Kłopotek
Abstract Mathematical Theory of Evidence (MTE) is known as a foundation for reasoning when knowledge is expressed at various levels of detail. Though much research effort has been committed to this theory since its foundation, many questions remain open. One of the most important open questions seems to be the relationship between frequencies and the Mathematical Theory of Evidence. The theory is blamed to leave frequencies outside (or aside of) its framework. The seriousness of this accusation is obvious: no experiment may be run to compare the performance of MTE-based models of real world processes against real world data. In this paper we develop a frequentist model of the MTE bringing to fall the above argument against MTE. We describe, how to interpret data in terms of MTE belief functions, how to reason from data about conditional belief functions, how to generate a random sample out of a MTE model, how to derive MTE model from data and how to compare results of reasoning in MTE model and reasoning from data. It is claimed in this paper that MTE is suitable to model some types of destructive processes
Tasks
Published 2018-11-09
URL http://arxiv.org/abs/1811.04790v1
PDF http://arxiv.org/pdf/1811.04790v1.pdf
PWC https://paperswithcode.com/paper/reasoning-from-data-in-the-mathematical
Repo
Framework

M2E-Try On Net: Fashion from Model to Everyone

Title M2E-Try On Net: Fashion from Model to Everyone
Authors Zhonghua Wu, Guosheng Lin, Qingyi Tao, Jianfei Cai
Abstract Most existing virtual try-on applications require clean clothes images. Instead, we present a novel virtual Try-On network, M2E-Try On Net, which transfers the clothes from a model image to a person image without the need of any clean product images. To obtain a realistic image of person wearing the desired model clothes, we aim to solve the following challenges: 1) non-rigid nature of clothes - we need to align poses between the model and the user; 2) richness in textures of fashion items - preserving the fine details and characteristics of the clothes is critical for photo-realistic transfer; 3) variation of identity appearances - it is required to fit the desired model clothes to the person identity seamlessly. To tackle these challenges, we introduce three key components, including the pose alignment network (PAN), the texture refinement network (TRN) and the fitting network (FTN). Since it is unlikely to gather image pairs of input person image and desired output image (i.e. person wearing the desired clothes), our framework is trained in a self-supervised manner to gradually transfer the poses and textures of the model’s clothes to the desired appearance. In the experiments, we verify on the Deep Fashion dataset and MVC dataset that our method can generate photo-realistic images for the person to try-on the model clothes. Furthermore, we explore the model capability for different fashion items, including both upper and lower garments.
Tasks
Published 2018-11-21
URL https://arxiv.org/abs/1811.08599v3
PDF https://arxiv.org/pdf/1811.08599v3.pdf
PWC https://paperswithcode.com/paper/m2e-try-on-net-fashion-from-model-to-everyone
Repo
Framework
comments powered by Disqus