May 7, 2019

2754 words 13 mins read

Paper Group ANR 156

Analysis of a Design Pattern for Teaching with Features and Labels. Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data. Learning Joint Feature Adaptation for Zero-Shot Recognition. A Theoretical Analysis of Deep Neural Networks for Texture Classification. Coordination Event Detection and Initiator Identi …

Analysis of a Design Pattern for Teaching with Features and Labels


Title	Analysis of a Design Pattern for Teaching with Features and Labels
Authors	Christopher Meek, Patrice Simard, Xiaojin Zhu
Abstract	We study the task of teaching a machine to classify objects using features and labels. We introduce the Error-Driven-Featuring design pattern for teaching using features and labels in which a teacher prefers to introduce features only if they are needed. We analyze the potential risks and benefits of this teaching pattern through the use of teaching protocols, illustrative examples, and by providing bounds on the effort required for an optimal machine teacher using a linear learning algorithm, the most commonly used type of learners in interactive machine learning systems. Our analysis provides a deeper understanding of potential trade-offs of using different learning algorithms and between the effort required for featuring (creating new features) and labeling (providing labels for objects).
Tasks
Published	2016-11-18
URL	http://arxiv.org/abs/1611.05950v1
PDF	http://arxiv.org/pdf/1611.05950v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-a-design-pattern-for-teaching
Repo
Framework

Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data


Title	Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
Authors	Xinghua Lou, Ken Kansky, Wolfgang Lehrach, CC Laan, Bhaskara Marthi, D. Scott Phoenix, Dileep George
Abstract	We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods. In addition to transcribing text from challenging images, our method performs fine-grained instance segmentation of characters. We show that our model is more robust to both affine transformations and non-affine deformations compared to previous approaches.
Tasks	Instance Segmentation, Scene Text Recognition, Semantic Segmentation
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02788v1
PDF	http://arxiv.org/pdf/1611.02788v1.pdf
PWC	https://paperswithcode.com/paper/generative-shape-models-joint-text
Repo
Framework

Learning Joint Feature Adaptation for Zero-Shot Recognition


Title	Learning Joint Feature Adaptation for Zero-Shot Recognition
Authors	Ziming Zhang, Venkatesh Saligrama
Abstract	Zero-shot recognition (ZSR) aims to recognize target-domain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative scarcity of source-domain features (e.g. one feature vector per class), which do not fully account for wide variability in target-domain instances. In this paper we propose a novel framework of learning data-dependent feature transforms for scoring similarity between an arbitrary pair of source and target data instances to account for the wide variability in target domain. Our proposed approach is based on optimizing over a parameterized family of local feature displacements that maximize the source-target adaptive similarity functions. Accordingly we propose formulating zero-shot learning (ZSL) using latent structural SVMs to learn our similarity functions from training data. As demonstration we design a specific algorithm under the proposed framework involving bilinear similarity functions and regularized least squares as penalties for feature displacement. We test our approach on several benchmark datasets for ZSR and show significant improvement over the state-of-the-art. For instance, on aP&Y dataset we can achieve 80.89% in terms of recognition accuracy, outperforming the state-of-the-art by 11.15%.
Tasks	Zero-Shot Learning
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07593v2
PDF	http://arxiv.org/pdf/1611.07593v2.pdf
PWC	https://paperswithcode.com/paper/learning-joint-feature-adaptation-for-zero
Repo
Framework

A Theoretical Analysis of Deep Neural Networks for Texture Classification


Title	A Theoretical Analysis of Deep Neural Networks for Texture Classification
Authors	Saikat Basu, Manohar Karki, Robert DiBiano, Supratik Mukhopadhyay, Sangram Ganguly, Ramakrishna Nemani, Shreekant Gayaka
Abstract	We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity.
Tasks	Object Recognition, Texture Classification
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02699v2
PDF	http://arxiv.org/pdf/1605.02699v2.pdf
PWC	https://paperswithcode.com/paper/a-theoretical-analysis-of-deep-neural
Repo
Framework

Coordination Event Detection and Initiator Identification in Time Series Data


Title	Coordination Event Detection and Initiator Identification in Time Series Data
Authors	Chainarong Amornbunchornvej, Ivan Brugere, Ariana Strandburg-Peshkin, Damien Farine, Margaret C. Crofoot, Tanya Y. Berger-Wolf
Abstract	Behavior initiation is a form of leadership and is an important aspect of social organization that affects the processes of group formation, dynamics, and decision-making in human societies and other social animal species. In this work, we formalize the “Coordination Initiator Inference Problem” and propose a simple yet powerful framework for extracting periods of coordinated activity and determining individuals who initiated this coordination, based solely on the activity of individuals within a group during those periods. The proposed approach, given arbitrary individual time series, automatically (1) identifies times of coordinated group activity, (2) determines the identities of initiators of those activities, and (3) classifies the likely mechanism by which the group coordination occurred, all of which are novel computational tasks. We demonstrate our framework on both simulated and real-world data: trajectories tracking of animals as well as stock market data. Our method is competitive with existing global leadership inference methods but provides the first approaches for local leadership and coordination mechanism classification. Our results are consistent with ground-truthed biological data and the framework finds many known events in financial data which are not otherwise reflected in the aggregate NASDAQ index. Our method is easily generalizable to any coordinated time-series data from interacting entities.
Tasks	Decision Making, Time Series
Published	2016-03-04
URL	https://arxiv.org/abs/1603.01570v2
PDF	https://arxiv.org/pdf/1603.01570v2.pdf
PWC	https://paperswithcode.com/paper/flica-a-framework-for-leader-identification
Repo
Framework

Single-Solution Hypervolume Maximization and its use for Improving Generalization of Neural Networks


Title	Single-Solution Hypervolume Maximization and its use for Improving Generalization of Neural Networks
Authors	Conrado S. Miranda, Fernando J. Von Zuben
Abstract	This paper introduces the hypervolume maximization with a single solution as an alternative to the mean loss minimization. The relationship between the two problems is proved through bounds on the cost function when an optimal solution to one of the problems is evaluated on the other, with a hyperparameter to control the similarity between the two problems. This same hyperparameter allows higher weight to be placed on samples with higher loss when computing the hypervolume’s gradient, whose normalized version can range from the mean loss to the max loss. An experiment on MNIST with a neural network is used to validate the theory developed, showing that the hypervolume maximization can behave similarly to the mean loss minimization and can also provide better performance, resulting on a 20% reduction of the classification error on the test set.
Tasks
Published	2016-02-03
URL	http://arxiv.org/abs/1602.01164v1
PDF	http://arxiv.org/pdf/1602.01164v1.pdf
PWC	https://paperswithcode.com/paper/single-solution-hypervolume-maximization-and
Repo
Framework

KOGNAC: Efficient Encoding of Large Knowledge Graphs


Title	KOGNAC: Efficient Encoding of Large Knowledge Graphs
Authors	Jacopo Urbani, Sourav Dutta, Sairam Gurajada, Gerhard Weikum
Abstract	Many Web applications require efficient querying of large Knowledge Graphs (KGs). We propose KOGNAC, a dictionary-encoding algorithm designed to improve SPARQL querying with a judicious combination of statistical and semantic techniques. In KOGNAC, frequent terms are detected with a frequency approximation algorithm and encoded to maximise compression. Infrequent terms are semantically grouped into ontological classes and encoded to increase data locality. We evaluated KOGNAC in combination with state-of-the-art RDF engines, and observed that it significantly improves SPARQL querying on KGs with up to 1B edges.
Tasks	Knowledge Graphs
Published	2016-04-16
URL	http://arxiv.org/abs/1604.04795v2
PDF	http://arxiv.org/pdf/1604.04795v2.pdf
PWC	https://paperswithcode.com/paper/kognac-efficient-encoding-of-large-knowledge
Repo
Framework

Large Angle based Skeleton Extraction for 3D Animation


Title	Large Angle based Skeleton Extraction for 3D Animation
Authors	Hugo Martin, Raphael Fernandez, Yong Khoo
Abstract	In this paper, we present a solution for arbitrary 3D character deformation by investigating rotation angle of decomposition and preserving the mesh topology structure. In computer graphics, skeleton extraction and skeleton-driven animation is an active areas and gains increasing interests from researchers. The accuracy is critical for realistic animation and related applications. There have been extensive studies on skeleton based 3D deformation. However for the scenarios of large angle rotation of different body parts, it has been relatively less addressed by the state-of-the-art, which often yield unsatisfactory results. Besides 3D animation problems, we also notice for many 3D skeleton detection or tracking applications from a video or depth streams, large angle rotation is also a critical factor in the regression accuracy and robustness. We introduced a distortion metric function to quantify the surface curviness before and after deformation, which is a major clue for large angle rotation detection. The intensive experimental results show that our method is suitable for 3D modeling, animation, skeleton based tracking applications.
Tasks
Published	2016-08-17
URL	http://arxiv.org/abs/1608.05045v1
PDF	http://arxiv.org/pdf/1608.05045v1.pdf
PWC	https://paperswithcode.com/paper/large-angle-based-skeleton-extraction-for-3d
Repo
Framework

Relative distance features for gait recognition with Kinect


Title	Relative distance features for gait recognition with Kinect
Authors	Ke Yang, Yong Dou, Shaohe Lv, Fei Zhang, Qi Lv
Abstract	Gait and static body measurement are important biometric technologies for passive human recognition. Many previous works argue that recognition performance based completely on the gait feature is limited. The reason for this limited performance remains unclear. This study focuses on human recognition with gait feature obtained by Kinect and shows that gait feature can effectively distinguish from different human beings through a novel representation – relative distance-based gait features. Experimental results show that the recognition accuracy with relative distance features reaches up to 85%, which is comparable with that of anthropometric features. The combination of relative distance features and anthropometric features can provide an accuracy of more than 95%. Results indicate that the relative distance feature is quite effective and worthy of further study in more general scenarios (e.g., without Kinect).
Tasks	Gait Recognition
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05415v1
PDF	http://arxiv.org/pdf/1605.05415v1.pdf
PWC	https://paperswithcode.com/paper/relative-distance-features-for-gait
Repo
Framework

Robust Ensemble Clustering Using Probability Trajectories


Title	Robust Ensemble Clustering Using Probability Trajectories
Authors	Dong Huang, Jian-Huang Lai, Chang-Dong Wang
Abstract	Although many successful ensemble clustering approaches have been developed in recent years, there are still two limitations to most of the existing approaches. First, they mostly overlook the issue of uncertain links, which may mislead the overall consensus process. Second, they generally lack the ability to incorporate global information to refine the local links. To address these two limitations, in this paper, we propose a novel ensemble clustering approach based on sparse graph representation and probability trajectory analysis. In particular, we present the elite neighbor selection strategy to identify the uncertain links by locally adaptive thresholds and build a sparse graph with a small number of probably reliable links. We argue that a small number of probably reliable links can lead to significantly better consensus results than using all graph links regardless of their reliability. The random walk process driven by a new transition probability matrix is utilized to explore the global information in the graph. We derive a novel and dense similarity measure from the sparse graph by analyzing the probability trajectories of the random walkers, based on which two consensus functions are further proposed. Experimental results on multiple real-world datasets demonstrate the effectiveness and efficiency of our approach.
Tasks
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01160v1
PDF	http://arxiv.org/pdf/1606.01160v1.pdf
PWC	https://paperswithcode.com/paper/robust-ensemble-clustering-using-probability
Repo
Framework

Osteoporotic and Neoplastic Compression Fracture Classification on Longitudinal CT


Title	Osteoporotic and Neoplastic Compression Fracture Classification on Longitudinal CT
Authors	Yinong Wang, Jianhua Yao, Joseph E. Burns, Ronald M. Summers
Abstract	Classification of vertebral compression fractures (VCF) having osteoporotic or neoplastic origin is fundamental to the planning of treatment. We developed a fracture classification system by acquiring quantitative morphologic and bone density determinants of fracture progression through the use of automated measurements from longitudinal studies. A total of 250 CT studies were acquired for the task, each having previously identified VCFs with osteoporosis or neoplasm. Thirty-six features or each identified VCF were computed and classified using a committee of support vector machines. Ten-fold cross validation on 695 identified fractured vertebrae showed classification accuracies of 0.812, 0.665, and 0.820 for the measured, longitudinal, and combined feature sets respectively.
Tasks
Published	2016-01-27
URL	http://arxiv.org/abs/1601.07533v1
PDF	http://arxiv.org/pdf/1601.07533v1.pdf
PWC	https://paperswithcode.com/paper/osteoporotic-and-neoplastic-compression
Repo
Framework

Optimizing Performance of Recurrent Neural Networks on GPUs


Title	Optimizing Performance of Recurrent Neural Networks on GPUs
Authors	Jeremy Appleyard, Tomas Kocisky, Phil Blunsom
Abstract	As recurrent neural networks become larger and deeper, training times for single networks are rising into weeks or even months. As such there is a significant incentive to improve the performance and scalability of these networks. While GPUs have become the hardware of choice for training and deploying recurrent models, the implementations employed often make use of only basic optimizations for these architectures. In this article we demonstrate that by exposing parallelism between operations within the network, an order of magnitude speedup across a range of network sizes can be achieved over a naive implementation. We describe three stages of optimization that have been incorporated into the fifth release of NVIDIA’s cuDNN: firstly optimizing a single cell, secondly a single layer, and thirdly the entire network.
Tasks
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01946v1
PDF	http://arxiv.org/pdf/1604.01946v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-performance-of-recurrent-neural
Repo
Framework

Is swarm intelligence able to create mazes?


Title	Is swarm intelligence able to create mazes?
Authors	Dawid Polap, Marcin Wozniak, Christian Napoli, Emiliano Tramontana
Abstract	In this paper, the idea of applying Computational Intelligence in the process of creation board games, in particular mazes, is presented. For two different algorithms the proposed idea has been examined. The results of the experiments are shown and discussed to present advantages and disadvantages.
Tasks	Board Games
Published	2016-01-25
URL	http://arxiv.org/abs/1601.06580v1
PDF	http://arxiv.org/pdf/1601.06580v1.pdf
PWC	https://paperswithcode.com/paper/is-swarm-intelligence-able-to-create-mazes
Repo
Framework

Optimistic Semi-supervised Least Squares Classification


Title	Optimistic Semi-supervised Least Squares Classification
Authors	Jesse H. Krijthe, Marco Loog
Abstract	The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be derived by applying block coordinate descent to two related but slightly different objective functions. The resulting soft-label approach is related to an idea about dealing with missing data that dates back to the 1930s. We show that the soft-label variant typically outperforms the hard-label variant on benchmark datasets and partially explain this behaviour by studying the relative difficulty of finding good local minima for the corresponding objective functions.
Tasks
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03713v1
PDF	http://arxiv.org/pdf/1610.03713v1.pdf
PWC	https://paperswithcode.com/paper/optimistic-semi-supervised-least-squares
Repo
Framework

Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks


Title	Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks
Authors	Li Yang Ku, Erik Learned-Miller, Rod Grupen
Abstract	In this work, we provide a solution for posturing the anthropomorphic Robonaut-2 hand and arm for grasping based on visual information. A mapping from visual features extracted from a convolutional neural network (CNN) to grasp points is learned. We demonstrate that a CNN pre-trained for image classification can be applied to a grasping task based on a small set of grasping examples. Our approach takes advantage of the hierarchical nature of the CNN by identifying features that capture the hierarchical support relations between filters in different CNN layers and locating their 3D positions by tracing activations backwards in the CNN. When this backward trace terminates in the RGB-D image, important manipulable structures are thereby localized. These features that reside in different layers of the CNN are then associated with controllers that engage different kinematic subchains in the hand/arm system for grasping. A grasping dataset is collected using demonstrated hand/object relationships for Robonaut-2 to evaluate the proposed approach in terms of the precision of the resulting preshape postures. We demonstrate that this approach outperforms baseline approaches in cluttered scenarios on the grasping dataset and a point cloud based approach on a grasping task using Robonaut-2.
Tasks	Image Classification
Published	2016-09-13
URL	http://arxiv.org/abs/1609.03947v5
PDF	http://arxiv.org/pdf/1609.03947v5.pdf
PWC	https://paperswithcode.com/paper/associating-grasp-configurations-with
Repo
Framework