May 5, 2019

2897 words 14 mins read

Paper Group ANR 502

Scale-Free Online Learning. Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings. A Novel Method for the Extrinsic Calibration of a 2D Laser Rangefinder and a Camera. Classification with Repulsion Tensors: A Case Study on Face Recognition. Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference …

Scale-Free Online Learning


Title	Scale-Free Online Learning
Authors	Francesco Orabona, Dávid Pál
Abstract	We design and analyze algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. Our algorithms are instances of the Follow the Regularized Leader (FTRL) and Mirror Descent (MD) meta-algorithms. We achieve adaptiveness to the norms of the loss vectors by scale invariance, i.e., our algorithms make exactly the same decisions if the sequence of loss vectors is multiplied by any positive constant. The algorithm based on FTRL works for any decision set, bounded or unbounded. For unbounded decisions sets, this is the first adaptive algorithm for online linear optimization with a non-vacuous regret bound. In contrast, we show lower bounds on scale-free algorithms based on MD on unbounded domains.
Tasks
Published	2016-01-08
URL	http://arxiv.org/abs/1601.01974v2
PDF	http://arxiv.org/pdf/1601.01974v2.pdf
PWC	https://paperswithcode.com/paper/scale-free-online-learning
Repo
Framework

Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings


Title	Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings
Authors	Fereshte Khani, Martin Rinard, Percy Liang
Abstract	Can we train a system that, on any new input, either says “don’t know” or makes a prediction that is guaranteed to be correct? We answer the question in the affirmative provided our model family is well-specified. Specifically, we introduce the unanimity principle: only predict when all models consistent with the training data predict the same output. We operationalize this principle for semantic parsing, the task of mapping utterances to logical forms. We develop a simple, efficient method that reasons over the infinite set of all consistent models by only checking two of the models. We prove that our method obtains 100% precision even with a modest amount of training data from a possibly adversarial distribution. Empirically, we demonstrate the effectiveness of our approach on the standard GeoQuery dataset.
Tasks	Semantic Parsing
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06368v2
PDF	http://arxiv.org/pdf/1606.06368v2.pdf
PWC	https://paperswithcode.com/paper/unanimous-prediction-for-100-precision-with
Repo
Framework

A Novel Method for the Extrinsic Calibration of a 2D Laser Rangefinder and a Camera


Title	A Novel Method for the Extrinsic Calibration of a 2D Laser Rangefinder and a Camera
Authors	Wenbo Dong, Volkan Isler
Abstract	We present a novel method for extrinsically calibrating a camera and a 2D Laser Rangefinder (LRF) whose beams are invisible from the camera image. We show that point-to-plane constraints from a single observation of a V-shaped calibration pattern composed of two non-coplanar triangles suffice to uniquely constrain the relative pose between two sensors. Next, we present an approach to obtain analytical solutions using point-to-plane constraints from single or multiple observations. Along the way, we also show that previous solutions, in contrast to our method, have inherent ambiguities and therefore must rely on a good initial estimate. Real and synthetic experiments validate our method and show that it achieves better accuracy than previous methods.
Tasks	Calibration
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04132v4
PDF	http://arxiv.org/pdf/1603.04132v4.pdf
PWC	https://paperswithcode.com/paper/a-novel-method-for-the-extrinsic-calibration
Repo
Framework

Classification with Repulsion Tensors: A Case Study on Face Recognition


Title	Classification with Repulsion Tensors: A Case Study on Face Recognition
Authors	Hawren Fang
Abstract	We consider dimensionality reduction methods for face recognition in a supervised setting, using an image-as-matrix representation. A common procedure is to project image matrices into a smaller space in which the recognition is performed. These methods are often called “two-dimensional” in the literature and there exist counterparts that use an image-as-vector representation. When two face images are close to each other in the input space they may remain close after projection - but this is not desirable in the situation when these two images are from different classes, and this often affects the recognition performance. We extend a previously developed `repulsion Laplacean’ technique based on adding terms to the objective function with the goal or creation a repulsion energy between such images in the projected space. This scheme, which relies on a repulsion graph, is generic and can be incorporated into various two-dimensional methods. It can be regarded as a multilinear generalization of the repulsion strategy by Kokiopoulou and Saad [Pattern Recog., 42 (2009), pp. 2392–2402]. Experimental results demonstrate that the proposed methodology offers significant recognition improvement relative to the underlying two-dimensional methods. \|
Tasks	Dimensionality Reduction, Face Recognition
Published	2016-03-15
URL	http://arxiv.org/abs/1603.04588v1
PDF	http://arxiv.org/pdf/1603.04588v1.pdf
PWC	https://paperswithcode.com/paper/classification-with-repulsion-tensors-a-case
Repo
Framework

Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference


Title	Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference
Authors	Vinay Venkataraman, Pavan Turaga
Abstract	This paper presents a shape-theoretic framework for dynamical analysis of nonlinear dynamical systems which appear frequently in several video-based inference tasks. Traditional approaches to dynamical modeling have included linear and nonlinear methods with their respective drawbacks. A novel approach we propose is the use of descriptors of the shape of the dynamical attractor as a feature representation of nature of dynamics. The proposed framework has two main advantages over traditional approaches: a) representation of the dynamical system is derived directly from the observational data, without any inherent assumptions, and b) the proposed features show stability under different time-series lengths where traditional dynamical invariants fail. We illustrate our idea using nonlinear dynamical models such as Lorenz and Rossler systems, where our feature representations (shape distribution) support our hypothesis that the local shape of the reconstructed phase space can be used as a discriminative feature. Our experimental analyses on these models also indicate that the proposed framework show stability for different time-series lengths, which is useful when the available number of samples are small/variable. The specific applications of interest in this paper are: 1) activity recognition using motion capture and RGBD sensors, 2) activity quality assessment for applications in stroke rehabilitation, and 3) dynamical scene classification. We provide experimental validation through action and gesture recognition experiments on motion capture and Kinect datasets. In all these scenarios, we show experimental evidence of the favorable properties of the proposed representation.
Tasks	Activity Recognition, Gesture Recognition, Motion Capture, Scene Classification, Time Series
Published	2016-01-27
URL	http://arxiv.org/abs/1601.07471v1
PDF	http://arxiv.org/pdf/1601.07471v1.pdf
PWC	https://paperswithcode.com/paper/shape-distributions-of-nonlinear-dynamical
Repo
Framework

Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference


Title	Adaptive Probabilistic Trajectory Optimization via Efficient Approximate Inference
Authors	Yunpeng Pan, Xinyan Yan, Evangelos Theodorou, Byron Boots
Abstract	Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the environment, it suffers from slow convergence. An alternative approach is Model Predictive Control (MPC), which optimizes policies quickly, but also requires accurate models of the system dynamics and environment. In this paper we propose a new approach, adaptive probabilistic trajectory optimization, that combines the benefits of RL and MPC. Our method uses scalable approximate inference to learn and updates probabilistic models in an online incremental fashion while also computing optimal control policies via successive local approximations. We present two variations of our algorithm based on the Sparse Spectrum Gaussian Process (SSGP) model, and we test our algorithm on three learning tasks, demonstrating the effectiveness and efficiency of our approach.
Tasks
Published	2016-08-22
URL	http://arxiv.org/abs/1608.06235v2
PDF	http://arxiv.org/pdf/1608.06235v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-probabilistic-trajectory
Repo
Framework

Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes


Title	Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes
Authors	Afonso Menegola, Michel Fornaciali, Ramon Pires, Sandra Avila, Eduardo Valle
Abstract	Deep learning is the current bet for image classification. Its greed for huge amounts of annotated data limits its usage in medical imaging context. In this scenario transfer learning appears as a prominent solution. In this report we aim to clarify how transfer learning schemes may influence classification results. We are particularly focused in the automated melanoma screening problem, a case of medical imaging in which transfer learning is still not widely used. We explored transfer with and without fine-tuning, sequential transfers and usage of pre-trained models in general and specific datasets. Although some issues remain open, our findings may drive future researches.
Tasks	Image Classification, Transfer Learning
Published	2016-09-05
URL	http://arxiv.org/abs/1609.01228v1
PDF	http://arxiv.org/pdf/1609.01228v1.pdf
PWC	https://paperswithcode.com/paper/towards-automated-melanoma-screening
Repo
Framework

Aerial image geolocalization from recognition and matching of roads and intersections


Title	Aerial image geolocalization from recognition and matching of roads and intersections
Authors	Dragos Costea, Marius Leordeanu
Abstract	Aerial image analysis at a semantic level is important in many applications with strong potential impact in industry and consumer use, such as automated mapping, urban planning, real estate and environment monitoring, or disaster relief. The problem is enjoying a great interest in computer vision and remote sensing, due to increased computer power and improvement in automated image understanding algorithms. In this paper we address the task of automatic geolocalization of aerial images from recognition and matching of roads and intersections. Our proposed method is a novel contribution in the literature that could enable many applications of aerial image analysis when GPS data is not available. We offer a complete pipeline for geolocalization, from the detection of roads and intersections, to the identification of the enclosing geographic region by matching detected intersections to previously learned manually labeled ones, followed by accurate geometric alignment between the detected roads and the manually labeled maps. We test on a novel dataset with aerial images of two European cities and use the publicly available OpenStreetMap project for collecting ground truth roads annotations. We show in extensive experiments that our approach produces highly accurate localizations in the challenging case when we train on images from one city and test on the other and the quality of the aerial images is relatively poor. We also show that the the alignment between detected roads and pre-stored manual annotations can be effectively used for improving the quality of the road detection results.
Tasks
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08323v1
PDF	http://arxiv.org/pdf/1605.08323v1.pdf
PWC	https://paperswithcode.com/paper/aerial-image-geolocalization-from-recognition
Repo
Framework

A Universal Approximation Theorem for Mixture of Experts Models


Title	A Universal Approximation Theorem for Mixture of Experts Models
Authors	Hien D Nguyen, Luke R Lloyd-Jones, Geoffrey J McLachlan
Abstract	The mixture of experts (MoE) model is a popular neural network architecture for nonlinear regression and classification. The class of MoE mean functions is known to be uniformly convergent to any unknown target function, assuming that the target function is from Sobolev space that is sufficiently differentiable and that the domain of estimation is a compact unit hypercube. We provide an alternative result, which shows that the class of MoE mean functions is dense in the class of all continuous functions over arbitrary compact domains of estimation. Our result can be viewed as a universal approximation theorem for MoE models.
Tasks
Published	2016-02-11
URL	http://arxiv.org/abs/1602.03683v1
PDF	http://arxiv.org/pdf/1602.03683v1.pdf
PWC	https://paperswithcode.com/paper/a-universal-approximation-theorem-for-mixture
Repo
Framework

Adaptive Image Denoising by Mixture Adaptation


Title	Adaptive Image Denoising by Mixture Adaptation
Authors	Enming Luo, Stanley H. Chan, Truong Q. Nguyen
Abstract	We propose an adaptive learning procedure to learn patch-based image priors for image denoising. The new algorithm, called the Expectation-Maximization (EM) adaptation, takes a generic prior learned from a generic external database and adapts it to the noisy image to generate a specific prior. Different from existing methods that combine internal and external statistics in ad-hoc ways, the proposed algorithm is rigorously derived from a Bayesian hyper-prior perspective. There are two contributions of this paper: First, we provide full derivation of the EM adaptation algorithm and demonstrate methods to improve the computational complexity. Second, in the absence of the latent clean image, we show how EM adaptation can be modified based on pre-filtering. Experimental results show that the proposed adaptation algorithm yields consistently better denoising results than the one without adaptation and is superior to several state-of-the-art algorithms.
Tasks	Denoising, Image Denoising
Published	2016-01-19
URL	http://arxiv.org/abs/1601.04770v3
PDF	http://arxiv.org/pdf/1601.04770v3.pdf
PWC	https://paperswithcode.com/paper/adaptive-image-denoising-by-mixture
Repo
Framework

Using Hadoop for Large Scale Analysis on Twitter: A Technical Report


Title	Using Hadoop for Large Scale Analysis on Twitter: A Technical Report
Authors	Nikolaos Nodarakis, Spyros Sioutas, Athanasios Tsakalidis, Giannis Tzimas
Abstract	Sentiment analysis (or opinion mining) on Twitter data has attracted much attention recently. One of the system’s key features, is the immediacy in communication with other users in an easy, user-friendly and fast way. Consequently, people tend to express their feelings freely, which makes Twitter an ideal source for accumulating a vast amount of opinions towards a wide diversity of topics. This amount of information offers huge potential and can be harnessed to receive the sentiment tendency towards these topics. However, since none can invest an infinite amount of time to read through these tweets, an automated decision making approach is necessary. Nevertheless, most existing solutions are limited in centralized environments only. Thus, they can only process at most a few thousand tweets. Such a sample, is not representative to define the sentiment polarity towards a topic due to the massive number of tweets published daily. In this paper, we go one step further and develop a novel method for sentiment learning in the MapReduce framework. Our algorithm exploits the hashtags and emoticons inside a tweet, as sentiment labels, and proceeds to a classification procedure of diverse sentiment types in a parallel and distributed manner. Moreover, we utilize Bloom filters to compact the storage size of intermediate data and boost the performance of our algorithm. Through an extensive experimental evaluation, we prove that our solution is efficient, robust and scalable and confirm the quality of our sentiment identification.
Tasks	Decision Making, Opinion Mining, Sentiment Analysis
Published	2016-02-03
URL	http://arxiv.org/abs/1602.01248v1
PDF	http://arxiv.org/pdf/1602.01248v1.pdf
PWC	https://paperswithcode.com/paper/using-hadoop-for-large-scale-analysis-on
Repo
Framework

Turning an Urban Scene Video into a Cinemagraph


Title	Turning an Urban Scene Video into a Cinemagraph
Authors	Hang Yan, Yebin Liu, Yasutaka Furukawa
Abstract	This paper proposes an algorithm that turns a regular video capturing urban scenes into a high-quality endless animation, known as a Cinemagraph. The creation of a Cinemagraph usually requires a static camera in a carefully configured scene. The task becomes challenging for a regular video with a moving camera and objects. Our approach first warps an input video into the viewpoint of a reference camera. Based on the warped video, we propose effective temporal analysis algorithms to detect regions with static geometry and dynamic appearance, where geometric modeling is reliable and visually attractive animations can be created. Lastly, the algorithm applies a sequence of video processing techniques to produce a Cinemagraph movie. We have tested the proposed approach on numerous challenging real scenes. To our knowledge, this work is the first to automatically generate Cinemagraph animations from regular movies in the wild.
Tasks
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01235v1
PDF	http://arxiv.org/pdf/1612.01235v1.pdf
PWC	https://paperswithcode.com/paper/turning-an-urban-scene-video-into-a
Repo
Framework

Noise Mitigation for Neural Entity Typing and Relation Extraction


Title	Noise Mitigation for Neural Entity Typing and Relation Extraction
Authors	Yadollah Yaghoobzadeh, Heike Adel, Hinrich Schütze
Abstract	In this paper, we address two different types of noise in information extraction models: noise from distant supervision and noise from pipeline input features. Our target tasks are entity typing and relation extraction. For the first noise type, we introduce multi-instance multi-label learning algorithms using neural network models, and apply them to fine-grained entity typing for the first time. This gives our models comparable performance with the state-of-the-art supervised approach which uses global embeddings of entities. For the second noise type, we propose ways to improve the integration of noisy entity type predictions into relation extraction. Our experiments show that probabilistic predictions are more robust than discrete predictions and that joint training of the two tasks performs best.
Tasks	Entity Typing, Multi-Label Learning, Relation Extraction
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07495v2
PDF	http://arxiv.org/pdf/1612.07495v2.pdf
PWC	https://paperswithcode.com/paper/noise-mitigation-for-neural-entity-typing-and
Repo
Framework

Improved Accent Classification Combining Phonetic Vowels with Acoustic Features


Title	Improved Accent Classification Combining Phonetic Vowels with Acoustic Features
Authors	Zhenhao Ge
Abstract	Researches have shown accent classification can be improved by integrating semantic information into pure acoustic approach. In this work, we combine phonetic knowledge, such as vowels, with enhanced acoustic features to build an improved accent classification system. The classifier is based on Gaussian Mixture Model-Universal Background Model (GMM-UBM), with normalized Perceptual Linear Predictive (PLP) features. The features are further optimized by Principle Component Analysis (PCA) and Hetroscedastic Linear Discriminant Analysis (HLDA). Using 7 major types of accented speech from the Foreign Accented English (FAE) corpus, the system achieves classification accuracy 54% with input test data as short as 20 seconds, which is competitive to the state of the art in this field.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07394v1
PDF	http://arxiv.org/pdf/1602.07394v1.pdf
PWC	https://paperswithcode.com/paper/improved-accent-classification-combining
Repo
Framework

Enhancing LambdaMART Using Oblivious Trees


Title	Enhancing LambdaMART Using Oblivious Trees
Authors	Michal Ferov, Marek Modrý
Abstract	Learning to rank is a machine learning technique broadly used in many areas such as document retrieval, collaborative filtering or question answering. We present experimental results which suggest that the performance of the current state-of-the-art learning to rank algorithm LambdaMART, when used for document retrieval for search engines, can be improved if standard regression trees are replaced by oblivious trees. This paper provides a comparison of both variants and our results demonstrate that the use of oblivious trees can improve the performance by more than $2.2%$. Additional experimental analysis of the influence of a number of features and of a size of the training set is also provided and confirms the desirability of properties of oblivious decision trees.
Tasks	Learning-To-Rank, Question Answering
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05610v1
PDF	http://arxiv.org/pdf/1609.05610v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-lambdamart-using-oblivious-trees
Repo
Framework