July 27, 2019

3127 words 15 mins read

Paper Group ANR 665

Big Data Classification Using Augmented Decision Trees. Ambiguity and Incomplete Information in Categorical Models of Language. Fashion Conversation Data on Instagram. Obstacle Avoidance Using Stereo Camera. ACCBench: A Framework for Comparing Causality Algorithms. Object-Oriented Knowledge Representation and Data Storage Using Inhomogeneous Classe …

Big Data Classification Using Augmented Decision Trees


Title	Big Data Classification Using Augmented Decision Trees
Authors	Rajiv Sambasivan, Sourish Das
Abstract	We present an algorithm for classification tasks on big data. Experiments conducted as part of this study indicate that the algorithm can be as accurate as ensemble methods such as random forests or gradient boosted trees. Unlike ensemble methods, the models produced by the algorithm can be easily interpreted. The algorithm is based on a divide and conquer strategy and consists of two steps. The first step consists of using a decision tree to segment the large dataset. By construction, decision trees attempt to create homogeneous class distributions in their leaf nodes. However, non-homogeneous leaf nodes are usually produced. The second step of the algorithm consists of using a suitable classifier to determine the class labels for the non-homogeneous leaf nodes. The decision tree segment provides a coarse segment profile while the leaf level classifier can provide information about the attributes that affect the label within a segment.
Tasks
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09567v1
PDF	http://arxiv.org/pdf/1710.09567v1.pdf
PWC	https://paperswithcode.com/paper/big-data-classification-using-augmented
Repo
Framework

Ambiguity and Incomplete Information in Categorical Models of Language


Title	Ambiguity and Incomplete Information in Categorical Models of Language
Authors	Dan Marsden
Abstract	We investigate notions of ambiguity and partial information in categorical distributional models of natural language. Probabilistic ambiguity has previously been studied using Selinger’s CPM construction. This construction works well for models built upon vector spaces, as has been shown in quantum computational applications. Unfortunately, it doesn’t seem to provide a satisfactory method for introducing mixing in other compact closed categories such as the category of sets and binary relations. We therefore lack a uniform strategy for extending a category to model imprecise linguistic information. In this work we adopt a different approach. We analyze different forms of ambiguous and incomplete information, both with and without quantitative probabilistic data. Each scheme then corresponds to a suitable enrichment of the category in which we model language. We view different monads as encapsulating the informational behaviour of interest, by analogy with their use in modelling side effects in computation. Previous results of Jacobs then allow us to systematically construct suitable bases for enrichment. We show that we can freely enrich arbitrary dagger compact closed categories in order to capture all the phenomena of interest, whilst retaining the important dagger compact closed structure. This allows us to construct a model with real convex combination of binary relations that makes non-trivial use of the scalars. Finally we relate our various different enrichments, showing that finite subconvex algebra enrichment covers all the effects under consideration.
Tasks
Published	2017-01-03
URL	http://arxiv.org/abs/1701.00660v1
PDF	http://arxiv.org/pdf/1701.00660v1.pdf
PWC	https://paperswithcode.com/paper/ambiguity-and-incomplete-information-in
Repo
Framework

Fashion Conversation Data on Instagram


Title	Fashion Conversation Data on Instagram
Authors	Yu-I Ha, Sejeong Kwon, Meeyoung Cha, Jungseock Joo
Abstract	The fashion industry is establishing its presence on a number of visual-centric social media like Instagram. This creates an interesting clash as fashion brands that have traditionally practiced highly creative and editorialized image marketing now have to engage with people on the platform that epitomizes impromptu, realtime conversation. What kinds of fashion images do brands and individuals share and what are the types of visual features that attract likes and comments? In this research, we take both quantitative and qualitative approaches to answer these questions. We analyze visual features of fashion posts first via manual tagging and then via training on convolutional neural networks. The classified images were examined across four types of fashion brands: mega couture, small couture, designers, and high street. We find that while product-only images make up the majority of fashion conversation in terms of volume, body snaps and face images that portray fashion items more naturally tend to receive a larger number of likes and comments by the audience. Our findings bring insights into building an automated tool for classifying or generating influential fashion information. We make our novel dataset of {24,752} labeled images on fashion conversations, containing visual and textual cues, available for the research community.
Tasks
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04137v1
PDF	http://arxiv.org/pdf/1704.04137v1.pdf
PWC	https://paperswithcode.com/paper/fashion-conversation-data-on-instagram
Repo
Framework

Obstacle Avoidance Using Stereo Camera


Title	Obstacle Avoidance Using Stereo Camera
Authors	Akkas Uddin Haque, Ashkan Nejadpak
Abstract	In this paper we present a novel method for obstacle avoidance using the stereo camera. The conventional obstacle avoidance methods and their limitations are discussed. A new algorithm is developed for the real-time obstacle avoidance which responds faster to unexpected obstacles. In this approach the depth map is divided into optimized number of regions and the minimum depth at each section is assigned as the depth of that region. A fuzzy controller is designed to create the drive commands for the robot/quadcopter. The system was tested on multiple paths with different obstacles and the results demonstrated the high accuracy of the developed system.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04114v2
PDF	http://arxiv.org/pdf/1705.04114v2.pdf
PWC	https://paperswithcode.com/paper/obstacle-avoidance-using-stereo-camera
Repo
Framework

ACCBench: A Framework for Comparing Causality Algorithms


Title	ACCBench: A Framework for Comparing Causality Algorithms
Authors	Simon Rehwald, Amjad Ibrahim, Kristian Beckers, Alexander Pretschner
Abstract	Modern socio-technical systems are increasingly complex. A fundamental problem is that the borders of such systems are often not well-defined a-priori, which among other problems can lead to unwanted behavior during runtime. Ideally, unwanted behavior should be prevented. If this is not possible the system shall at least be able to help determine potential cause(s) a-posterori, identify responsible parties and make them accountable for their behavior. Recently, several algorithms addressing these concepts have been proposed. However, the applicability of the corresponding approaches, specifically their effectiveness and performance, is mostly unknown. Therefore, in this paper, we propose ACCBench, a benchmark tool that allows to compare and evaluate causality algorithms under a consistent setting. Furthermore, we contribute an implementation of the two causality algorithms by G"o{\ss}ler and Metayer and G"o{\ss}ler and Astefanoaei as well as of a policy compliance approach based on some concepts of Main et al. Lastly, we conduct a case study of an Intelligent Door Control System, which exposes concrete strengths and weaknesses of all algorithms under different aspects. In the course of this, we show that the effectiveness of the algorithms in terms of cause detection as well as their performance differ to some extent. In addition, our analysis reports on some qualitative aspects that should be considered when evaluating each algorithm. For example, the human effort needed to configure the algorithm and model the use case is analyzed.
Tasks
Published	2017-10-10
URL	http://arxiv.org/abs/1710.05720v1
PDF	http://arxiv.org/pdf/1710.05720v1.pdf
PWC	https://paperswithcode.com/paper/accbench-a-framework-for-comparing-causality
Repo
Framework

Object-Oriented Knowledge Representation and Data Storage Using Inhomogeneous Classes


Title	Object-Oriented Knowledge Representation and Data Storage Using Inhomogeneous Classes
Authors	Dmytro Terletskyi
Abstract	This paper contains analysis of concept of a class within different object-oriented knowledge representation models. The main attention is paid to structure of the class and its efficiency in the context of data storage, using object-relational mapping. The main achievement of the paper is extension of concept of homogeneous class of objects by introducing concepts of single-core and multi-core inhomogeneous classes of objects, which allow simultaneous defining of a few different types within one class of objects, avoiding duplication of properties and methods in representation of types, decreasing sizes of program codes and providing more efficient information storage in the databases. In addition, the paper contains results of experiment, which show that data storage in relational database, using proposed extensions of the class, in some cases is more efficient in contrast to usage of homogeneous classes of objects.
Tasks
Published	2017-09-23
URL	http://arxiv.org/abs/1709.08027v1
PDF	http://arxiv.org/pdf/1709.08027v1.pdf
PWC	https://paperswithcode.com/paper/object-oriented-knowledge-representation-and
Repo
Framework

First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time


Title	First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time
Authors	Yi Xu, Rong Jin, Tianbao Yang
Abstract	Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the first-order information. The existing analysis for algorithms using noise in the first-order information is quite involved and hides the essence of added noise, which hinder further improvements of these algorithms. In this paper, we present a novel perspective of noise-adding technique, i.e., adding the noise into the first-order information can help extract the negative curvature from the Hessian matrix, and provide a formal reasoning of this perspective by analyzing a simple first-order procedure. More importantly, the proposed procedure enables one to design purely first-order stochastic algorithms for escaping from non-degenerate saddle points with a much better time complexity (almost linear time in terms of the problem’s dimensionality). In particular, we develop a {\bf first-order stochastic algorithm} based on our new technique and an existing algorithm that only converges to a first-order stationary point to enjoy a time complexity of {$\widetilde O(d/\epsilon^{3.5})$ for finding a nearly second-order stationary point $\bf{x}$ such that $\nabla F(bf{x})\leq \epsilon$ and $\nabla^2 F(bf{x})\geq -\sqrt{\epsilon}I$ (in high probability), where $F(\cdot)$ denotes the objective function and $d$ is the dimensionality of the problem. To the best of our knowledge, this is the best theoretical result of first-order algorithms for stochastic non-convex optimization, which is even competitive with if not better than existing stochastic algorithms hinging on the second-order information.
Tasks
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01944v3
PDF	http://arxiv.org/pdf/1711.01944v3.pdf
PWC	https://paperswithcode.com/paper/first-order-stochastic-algorithms-for
Repo
Framework

Autocompletion interfaces make crowd workers slower, but their use promotes response diversity


Title	Autocompletion interfaces make crowd workers slower, but their use promotes response diversity
Authors	Xipei Liu, James P. Bagrow
Abstract	Creative tasks such as ideation or question proposal are powerful applications of crowdsourcing, yet the quantity of workers available for addressing practical problems is often insufficient. To enable scalable crowdsourcing thus requires gaining all possible efficiency and information from available workers. One option for text-focused tasks is to allow assistive technology, such as an autocompletion user interface (AUI), to help workers input text responses. But support for the efficacy of AUIs is mixed. Here we designed and conducted a randomized experiment where workers were asked to provide short text responses to given questions. Our experimental goal was to determine if an AUI helps workers respond more quickly and with improved consistency by mitigating typos and misspellings. Surprisingly, we found that neither occurred: workers assigned to the AUI treatment were slower than those assigned to the non-AUI control and their responses were more diverse, not less, than those of the control. Both the lexical and semantic diversities of responses were higher, with the latter measured using word2vec. A crowdsourcer interested in worker speed may want to avoid using an AUI, but using an AUI to boost response diversity may be valuable to crowdsourcers interested in receiving as much novel information from workers as possible.
Tasks
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06939v1
PDF	http://arxiv.org/pdf/1707.06939v1.pdf
PWC	https://paperswithcode.com/paper/autocompletion-interfaces-make-crowd-workers
Repo
Framework

Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks


Title	Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks
Authors	Brady Kieffer, Morteza Babaie, Shivam Kalra, H. R. Tizhoosh
Abstract	We explore the problem of classification within a medical image data-set based on a feature vector extracted from the deepest layer of pre-trained Convolution Neural Networks. We have used feature vectors from several pre-trained structures, including networks with/without transfer learning to evaluate the performance of pre-trained deep features versus CNNs which have been trained by that specific dataset as well as the impact of transfer learning with a small number of samples. All experiments are done on Kimia Path24 dataset which consists of 27,055 histopathology training patches in 24 tissue texture classes along with 1,325 test patches for evaluation. The result shows that pre-trained networks are quite competitive against training from scratch. As well, fine-tuning does not seem to add any tangible improvement for VGG16 to justify additional training while we observed considerable improvement in retrieval and classification accuracy when we fine-tuned the Inception structure.
Tasks	Image Classification, Transfer Learning
Published	2017-10-11
URL	http://arxiv.org/abs/1710.05726v1
PDF	http://arxiv.org/pdf/1710.05726v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-1
Repo
Framework

Vehicle Speed Detecting App


Title	Vehicle Speed Detecting App
Authors	Itoro Ikon
Abstract	The report presents the measurement of vehicular speed using a smartphone camera. The speed measurement is accomplished by detecting the position of the vehicle on a camera frame using the LBP cascade classifier of OpenCV API, the displacement of the detected vehicle with time is used to compute the speed. Conversion coefficient is determined to map the pixel displacement to actual vehicle distance. The speeds measured are proportional to the ground truth speeds.
Tasks
Published	2017-02-17
URL	http://arxiv.org/abs/1702.05388v2
PDF	http://arxiv.org/pdf/1702.05388v2.pdf
PWC	https://paperswithcode.com/paper/vehicle-speed-detecting-app
Repo
Framework

f-Divergence constrained policy improvement


Title	f-Divergence constrained policy improvement
Authors	Boris Belousov, Jan Peters
Abstract	To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of distance well but also yields closed-form solutions. In this paper, we consider a more general class of f-divergences and derive the corresponding policy update rules. The generic solution is expressed through the derivative of the convex conjugate function to f and includes the KL solution as a special case. Within the class of f-divergences, we further focus on a one-parameter family of $\alpha$-divergences to study effects of the choice of divergence on policy improvement. Previously known as well as new policy updates emerge for different values of $\alpha$. We show that every type of policy update comes with a compatible policy evaluation resulting from the chosen f-divergence. Interestingly, the mean-squared Bellman error minimization is closely related to policy evaluation with the Pearson $\chi^2$-divergence penalty, while the KL divergence results in the soft-max policy update and a log-sum-exp critic. We carry out asymptotic analysis of the solutions for different values of $\alpha$ and demonstrate the effects of using different divergence functions on a multi-armed bandit problem and on common standard reinforcement learning problems.
Tasks
Published	2017-12-29
URL	http://arxiv.org/abs/1801.00056v2
PDF	http://arxiv.org/pdf/1801.00056v2.pdf
PWC	https://paperswithcode.com/paper/f-divergence-constrained-policy-improvement
Repo
Framework

Learning a 3D descriptor for cross-source point cloud registration from synthetic data


Title	Learning a 3D descriptor for cross-source point cloud registration from synthetic data
Authors	Xiaoshui Huang
Abstract	As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because of the variant of density, missing data, different viewpoint, noise and outliers, and geometric transformation. In this paper, we propose a method to learn a 3D descriptor for finding the correspondent relations between these challenging point clouds. To train the deep learning framework, we use synthetic 3D point cloud as input. Starting from synthetic dataset, we use region-based sampling method to select reasonable, large and diverse training samples from synthetic samples. Then, we use data augmentation to extend our network be robust to rotation transformation. We focus our work on more general cases that point clouds coming from different sensors, named cross-source point cloud. The experiments show that our descriptor is not only able to generalize to new scenes, but also generalize to different sensors. The results demonstrate that the proposed method successfully aligns two 3D cross-source point clouds which outperforms state-of-the-art method.
Tasks	Data Augmentation, Point Cloud Registration
Published	2017-08-24
URL	http://arxiv.org/abs/1708.08997v1
PDF	http://arxiv.org/pdf/1708.08997v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-3d-descriptor-for-cross-source
Repo
Framework

Tree-Structured Reinforcement Learning for Sequential Object Localization


Title	Tree-Structured Reinforcement Learning for Sequential Object Localization
Authors	Zequn Jie, Xiaodan Liang, Jiashi Feng, Xiaojie Jin, Wen Feng Lu, Shuicheng Yan
Abstract	Existing object proposal algorithms usually search for possible object regions over multiple locations and scales separately, which ignore the interdependency among different objects and deviate from the human perception procedure. To incorporate global interdependency between objects into object localization, we propose an effective Tree-structured Reinforcement Learning (Tree-RL) approach to sequentially search for objects by fully exploiting both the current observation and historical search paths. The Tree-RL approach learns multiple searching policies through maximizing the long-term reward that reflects localization accuracies over all the objects. Starting with taking the entire image as a proposal, the Tree-RL approach allows the agent to sequentially discover multiple objects via a tree-structured traversing scheme. Allowing multiple near-optimal policies, Tree-RL offers more diversity in search paths and is able to find multiple objects with a single feed-forward pass. Therefore, Tree-RL can better cover different objects with various scales which is quite appealing in the context of object proposal. Experiments on PASCAL VOC 2007 and 2012 validate the effectiveness of the Tree-RL, which can achieve comparable recalls with current object proposal algorithms via much fewer candidate windows.
Tasks	Object Localization
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02710v1
PDF	http://arxiv.org/pdf/1703.02710v1.pdf
PWC	https://paperswithcode.com/paper/tree-structured-reinforcement-learning-for
Repo
Framework

Algorithmic stability and hypothesis complexity


Title	Algorithmic stability and hypothesis complexity
Authors	Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao
Abstract	We introduce a notion of algorithmic stability of learning algorithms—that we term \emph{argument stability}—that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of any learning algorithm in terms of its argument stability. The bounds are based on martingale inequalities in the Banach space to which the hypotheses belong. We apply the general bounds to bound the performance of some learning algorithms based on empirical risk minimization and stochastic gradient descent.
Tasks
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08712v2
PDF	http://arxiv.org/pdf/1702.08712v2.pdf
PWC	https://paperswithcode.com/paper/algorithmic-stability-and-hypothesis
Repo
Framework

Towards Vision-Based Smart Hospitals: A System for Tracking and Monitoring Hand Hygiene Compliance


Title	Towards Vision-Based Smart Hospitals: A System for Tracking and Monitoring Hand Hygiene Compliance
Authors	Albert Haque, Michelle Guo, Alexandre Alahi, Serena Yeung, Zelun Luo, Alisha Rege, Jeffrey Jopling, Lance Downing, William Beninati, Amit Singh, Terry Platchek, Arnold Milstein, Li Fei-Fei
Abstract	One in twenty-five patients admitted to a hospital will suffer from a hospital acquired infection. If we can intelligently track healthcare staff, patients, and visitors, we can better understand the sources of such infections. We envision a smart hospital capable of increasing operational efficiency and improving patient care with less spending. In this paper, we propose a non-intrusive vision-based system for tracking people’s activity in hospitals. We evaluate our method for the problem of measuring hand hygiene compliance. Empirically, our method outperforms existing solutions such as proximity-based techniques and covert in-person observational studies. We present intuitive, qualitative results that analyze human movement patterns and conduct spatial analytics which convey our method’s interpretability. This work is a step towards a computer-vision based smart hospital and demonstrates promising results for reducing hospital acquired infections.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00163v3
PDF	http://arxiv.org/pdf/1708.00163v3.pdf
PWC	https://paperswithcode.com/paper/towards-vision-based-smart-hospitals-a-system
Repo
Framework