May 5, 2019

3294 words 16 mins read

Paper Group ANR 475

A Spatio-Temporal Representation for the Orienteering Problem with Time-Varying Profits. On Reducing the Number of Visual Words in the Bag-of-Features Representation. UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS. Content-Based Top-N Recommendation using Heterogeneous Relations. Alternating optimi …

A Spatio-Temporal Representation for the Orienteering Problem with Time-Varying Profits


Title	A Spatio-Temporal Representation for the Orienteering Problem with Time-Varying Profits
Authors	Zhibei Ma, Kai Yin, Lantao Liu, Gaurav S. Sukhatme
Abstract	We consider an orienteering problem (OP) where an agent needs to visit a series (possibly a subset) of depots, from which the maximal accumulated profits are desired within given limited time budget. Different from most existing works where the profits are assumed to be static, in this work we investigate a variant that has arbitrary time-dependent profits. Specifically, the profits to be collected change over time and they follow different (e.g., independent) time-varying functions. The problem is of inherent nonlinearity and difficult to solve by existing methods. To tackle the challenge, we present a simple and effective framework that incorporates time-variations into the fundamental planning process. Specifically, we propose a deterministic spatio-temporal representation where both spatial description and temporal logic are unified into one routing topology. By employing existing basic sorting and searching algorithms, the routing solutions can be computed in an extremely efficient way. The proposed method is easy to implement and extensive numerical results show that our approach is time efficient and generates near-optimal solutions.
Tasks
Published	2016-11-24
URL	http://arxiv.org/abs/1611.08037v2
PDF	http://arxiv.org/pdf/1611.08037v2.pdf
PWC	https://paperswithcode.com/paper/a-spatio-temporal-representation-for-the
Repo
Framework

On Reducing the Number of Visual Words in the Bag-of-Features Representation


Title	On Reducing the Number of Visual Words in the Bag-of-Features Representation
Authors	Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro
Abstract	A new class of applications based on visual search engines are emerging, especially on smart-phones that have evolved into powerful tools for processing images and videos. The state-of-the-art algorithms for large visual content recognition and content based similarity search today use the “Bag of Features” (BoF) or “Bag of Words” (BoW) approach. The idea, borrowed from text retrieval, enables the use of inverted files. A very well known issue with this approach is that the query images, as well as the stored data, are described with thousands of words. This poses obvious efficiency problems when using inverted files to perform efficient image matching. In this paper, we propose and compare various techniques to reduce the number of words describing an image to improve efficiency and we study the effects of this reduction on effectiveness in landmark recognition and retrieval scenarios. We show that very relevant improvement in performance are achievable still preserving the advantages of the BoF base approach.
Tasks
Published	2016-04-14
URL	http://arxiv.org/abs/1604.04142v1
PDF	http://arxiv.org/pdf/1604.04142v1.pdf
PWC	https://paperswithcode.com/paper/on-reducing-the-number-of-visual-words-in-the
Repo
Framework

UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS


Title	UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS
Authors	Tathagata Chakraborti, Kartik Talamadupula, Kshitij P. Fadnis, Murray Campbell, Subbarao Kambhampati
Abstract	In this paper, we present UbuntuWorld 1.0 LTS - a platform for developing automated technical support agents in the Ubuntu operating system. Specifically, we propose to use the Bash terminal as a simulator of the Ubuntu environment for a learning-based agent and demonstrate the usefulness of adopting reinforcement learning (RL) techniques for basic problem solving and troubleshooting in this environment. We provide a plug-and-play interface to the simulator as a python package where different types of agents can be plugged in and evaluated, and provide pathways for integrating data from online support forums like AskUbuntu into an automated agent’s learning process. Finally, we show that the use of this data significantly improves the agent’s learning efficiency. We believe that this platform can be adopted as a real-world test bed for research on automated technical support.
Tasks
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08524v2
PDF	http://arxiv.org/pdf/1609.08524v2.pdf
PWC	https://paperswithcode.com/paper/ubuntuworld-10-lts-a-platform-for-automated
Repo
Framework

Content-Based Top-N Recommendation using Heterogeneous Relations


Title	Content-Based Top-N Recommendation using Heterogeneous Relations
Authors	Yifan Chen, Xiang Zhao, Junjiao Gan, Junkai Ren, Yang Fang
Abstract	Top-$N$ recommender systems have been extensively studied. However, the sparsity of user-item activities has not been well resolved. While many hybrid systems were proposed to address the cold-start problem, the profile information has not been sufficiently leveraged. Furthermore, the heterogeneity of profiles between users and items intensifies the challenge. In this paper, we propose a content-based top-$N$ recommender system by learning the global term weights in profiles. To achieve this, we bring in PathSim, which could well measures the node similarity with heterogeneous relations (between users and items). Starting from the original TF-IDF value, the global term weights gradually converge, and eventually reflect both profile and activity information. To facilitate training, the derivative is reformulated into matrix form, which could easily be paralleled. We conduct extensive experiments, which demonstrate the superiority of the proposed method.
Tasks	Recommendation Systems
Published	2016-06-27
URL	http://arxiv.org/abs/1606.08104v1
PDF	http://arxiv.org/pdf/1606.08104v1.pdf
PWC	https://paperswithcode.com/paper/content-based-top-n-recommendation-using
Repo
Framework

Alternating optimization method based on nonnegative matrix factorizations for deep neural networks


Title	Alternating optimization method based on nonnegative matrix factorizations for deep neural networks
Authors	Tetsuya Sakurai, Akira Imakura, Yuto Inoue, Yasunori Futamura
Abstract	The backpropagation algorithm for calculating gradients has been widely used in computation of weights for deep neural networks (DNNs). This method requires derivatives of objective functions and has some difficulties finding appropriate parameters such as learning rate. In this paper, we propose a novel approach for computing weight matrices of fully-connected DNNs by using two types of semi-nonnegative matrix factorizations (semi-NMFs). In this method, optimization processes are performed by calculating weight matrices alternately, and backpropagation (BP) is not used. We also present a method to calculate stacked autoencoder using a NMF. The output results of the autoencoder are used as pre-training data for DNNs. The experimental results show that our method using three types of NMFs attains similar error rates to the conventional DNNs with BP.
Tasks
Published	2016-05-16
URL	http://arxiv.org/abs/1605.04639v1
PDF	http://arxiv.org/pdf/1605.04639v1.pdf
PWC	https://paperswithcode.com/paper/alternating-optimization-method-based-on
Repo
Framework

Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets


Title	Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets
Authors	Ayush Mittal, Anant Raj, Vinay P. Namboodiri, Tinne Tuytelaars
Abstract	The goal of domain adaptation is to adapt models learned on a source domain to a particular target domain. Most methods for unsupervised domain adaptation proposed in the literature to date, assume that the set of classes present in the target domain is identical to the set of classes present in the source domain. This is a restrictive assumption that limits the practical applicability of unsupervised domain adaptation techniques in real world settings (“in the wild”). Therefore, we relax this constraint and propose a technique that allows the set of target classes to be a subset of the source classes. This way, large publicly available annotated datasets with a wide variety of classes can be used as source, even if the actual set of classes in target can be more limited and, maybe most importantly, unknown beforehand. To this end, we propose an algorithm that orders a set of source subspaces that are relevant to the target classification problem. Our method then chooses a restricted set from this ordered set of source subspaces. As an extension, even starting from multiple source datasets with varied sets of categories, this method automatically selects an appropriate subset of source categories relevant to a target dataset. Empirical analysis on a number of source and target domain datasets shows that restricting the source subspace to only a subset of categories does indeed substantially improve the eventual target classification accuracy over the baseline that considers all source classes.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2016-03-26
URL	http://arxiv.org/abs/1603.08105v1
PDF	http://arxiv.org/pdf/1603.08105v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-domain-adaptation-in-the-wild
Repo
Framework

Novelty Learning via Collaborative Proximity Filtering


Title	Novelty Learning via Collaborative Proximity Filtering
Authors	Arun Kumar, Paul Schrater
Abstract	The vast majority of recommender systems model preferences as static or slowly changing due to observable user experience. However, spontaneous changes in user preferences are ubiquitous in many domains like media consumption and key factors that drive changes in preferences are not directly observable. These latent sources of preference change pose new challenges. When systems do not track and adapt to users’ tastes, users lose confidence and trust, increasing the risk of user churn. We meet these challenges by developing a model of novelty preferences that learns and tracks latent user tastes. We combine three innovations: a new measure of item similarity based on patterns of consumption co-occurrence; model for {\em spontaneous} changes in preferences; and a learning agent that tracks each user’s dynamic preferences and learns individualized policies for variety. The resulting framework adaptively provides users with novelty tailored to their preferences for change per se.
Tasks	Recommendation Systems
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06633v1
PDF	http://arxiv.org/pdf/1610.06633v1.pdf
PWC	https://paperswithcode.com/paper/novelty-learning-via-collaborative-proximity
Repo
Framework

Using Machine Learning to Detect Noisy Neighbors in 5G Networks


Title	Using Machine Learning to Detect Noisy Neighbors in 5G Networks
Authors	Udi Margolin, Alberto Mozo, Bruno Ordozgoiti, Danny Raz, Elisha Rosensweig, Itai Segall
Abstract	5G networks are expected to be more dynamic and chaotic in their structure than current networks. With the advent of Network Function Virtualization (NFV), Network Functions (NF) will no longer be tightly coupled with the hardware they are running on, which poses new challenges in network management. Noisy neighbor is a term commonly used to describe situations in NFV infrastructure where an application experiences degradation in performance due to the fact that some of the resources it needs are occupied by other applications in the same cloud node. These situations cannot be easily identified using straightforward approaches, which calls for the use of sophisticated methods for NFV infrastructure management. In this paper we demonstrate how Machine Learning (ML) techniques can be used to identify such events. Through experiments using data collected at real NFV infrastructure, we show that standard models for automated classification can detect the noisy neighbor phenomenon with an accuracy of more than 90% in a simple scenario.
Tasks
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07419v1
PDF	http://arxiv.org/pdf/1610.07419v1.pdf
PWC	https://paperswithcode.com/paper/using-machine-learning-to-detect-noisy
Repo
Framework

FLIC: Fast Linear Iterative Clustering with Active Search


Title	FLIC: Fast Linear Iterative Clustering with Active Search
Authors	Jiaxing Zhao, Ren Bo, Qibin Hou, Ming-Ming Cheng, Paul L. Rosin
Abstract	Benefiting from its high efficiency and simplicity, Simple Linear Iterative Clustering (SLIC) remains one of the most popular over-segmentation tools. However, due to explicit enforcement of spatial similarity for region continuity, the boundary adaptation of SLIC is sub-optimal. It also has drawbacks on convergence rate as a result of both the fixed search region and separately doing the assignment step and the update step. In this paper, we propose an alternative approach to fix the inherent limitations of SLIC. In our approach, each pixel actively searches its corresponding segment under the help of its neighboring pixels, which naturally enables region coherence without being harmful to boundary adaptation. We also jointly perform the assignment and update steps, allowing high convergence rate. Extensive evaluations on Berkeley segmentation benchmark verify that our method outperforms competitive methods under various evaluation metrics. It also has the lowest time cost among existing methods (approximately 30fps for a 481x321 image on a single CPU core).
Tasks
Published	2016-12-06
URL	http://arxiv.org/abs/1612.01810v3
PDF	http://arxiv.org/pdf/1612.01810v3.pdf
PWC	https://paperswithcode.com/paper/flic-fast-linear-iterative-clustering-with
Repo
Framework

Egocentric Height Estimation


Title	Egocentric Height Estimation
Authors	Jessica Finocchiaro, Aisha Urooj Khan, Ali Borji
Abstract	Egocentric, or first-person vision which became popular in recent years with an emerge in wearable technology, is different than exocentric (third-person) vision in some distinguishable ways, one of which being that the camera wearer is generally not visible in the video frames. Recent work has been done on action and object recognition in egocentric videos, as well as work on biometric extraction from first-person videos. Height estimation can be a useful feature for both soft-biometrics and object tracking. Here, we propose a method of estimating the height of an egocentric camera without any calibration or reference points. We used both traditional computer vision approaches and deep learning in order to determine the visual cues that results in best height estimation. Here, we introduce a framework inspired by two stream networks comprising of two Convolutional Neural Networks, one based on spatial information, and one based on information given by optical flow in a frame. Given an egocentric video as an input to the framework, our model yields a height estimate as an output. We also incorporate late fusion to learn a combination of temporal and spatial cues. Comparing our model with other methods we used as baselines, we achieve height estimates for videos with a Mean Average Error of 14.04 cm over a range of 103 cm of data, and classification accuracy for relative height (tall, medium or short) up to 93.75% where chance level is 33%.
Tasks	Calibration, Object Recognition, Object Tracking, Optical Flow Estimation
Published	2016-10-09
URL	http://arxiv.org/abs/1610.02714v1
PDF	http://arxiv.org/pdf/1610.02714v1.pdf
PWC	https://paperswithcode.com/paper/egocentric-height-estimation
Repo
Framework

Multiclass Classification Calibration Functions


Title	Multiclass Classification Calibration Functions
Authors	Bernardo Ávila Pires, Csaba Szepesvári
Abstract	In this paper we refine the process of computing calibration functions for a number of multiclass classification surrogate losses. Calibration functions are a powerful tool for easily converting bounds for the surrogate risk (which can be computed through well-known methods) into bounds for the true risk, the probability of making a mistake. They are particularly suitable in non-parametric settings, where the approximation error can be controlled, and provide tighter bounds than the common technique of upper-bounding the 0-1 loss by the surrogate loss. The abstract nature of the more sophisticated existing calibration function results requires calibration functions to be explicitly derived on a case-by-case basis, requiring repeated efforts whenever bounds for a new surrogate loss are required. We devise a streamlined analysis that simplifies the process of deriving calibration functions for a large number of surrogate losses that have been proposed in the literature. The effort of deriving calibration functions is then surmised in verifying, for a chosen surrogate loss, a small number of conditions that we introduce. As case studies, we recover existing calibration functions for the well-known loss of Lee et al. (2004), and also provide novel calibration functions for well-known losses, including the one-versus-all loss and the logistic regression loss, plus a number of other losses that have been shown to be classification-calibrated in the past, but for which no calibration function had been derived.
Tasks	Calibration
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06385v1
PDF	http://arxiv.org/pdf/1609.06385v1.pdf
PWC	https://paperswithcode.com/paper/multiclass-classification-calibration
Repo
Framework

Fully-Automatic Synapse Prediction and Validation on a Large Data Set


Title	Fully-Automatic Synapse Prediction and Validation on a Large Data Set
Authors	Gary B. Huang, Louis K. Scheffer, Stephen M. Plaza
Abstract	Extracting a connectome from an electron microscopy (EM) data set requires identification of neurons and determination of synapses between neurons. As manual extraction of this information is very time-consuming, there has been extensive research effort to automatically segment the neurons to help guide and eventually replace manual tracing. Until recently, there has been comparatively less research on automatically detecting the actual synapses between neurons. This discrepancy can, in part, be attributed to several factors: obtaining neuronal shapes is a prerequisite first step in extracting a connectome, manual tracing is much more time-consuming than annotating synapses, and neuronal contact area can be used as a proxy for synapses in determining connections. However, recent research has demonstrated that contact area alone is not a sufficient predictor of synaptic connection. Moreover, as segmentation has improved, we have observed that synapse annotation is consuming a more significant fraction of overall reconstruction time. This ratio will only get worse as segmentation improves, gating overall possible speed-up. Therefore, we address this problem by developing algorithms that automatically detect pre-synaptic neurons and their post-synaptic partners. In particular, pre-synaptic structures are detected using a Deep and Wide Multiscale Recursive Network, and post-synaptic partners are detected using a MLP with features conditioned on the local segmentation. This work is novel because it requires minimal amount of training, leverages advances in image segmentation directly, and provides a complete solution for polyadic synapse detection. We further introduce novel metrics to evaluate our algorithm on connectomes of meaningful size. These metrics demonstrate that complete automatic prediction can be used to effectively characterize most connectivity correctly.
Tasks	Semantic Segmentation
Published	2016-04-11
URL	http://arxiv.org/abs/1604.03075v1
PDF	http://arxiv.org/pdf/1604.03075v1.pdf
PWC	https://paperswithcode.com/paper/fully-automatic-synapse-prediction-and
Repo
Framework

Fast learning rates with heavy-tailed losses


Title	Fast learning rates with heavy-tailed losses
Authors	Vu Dinh, Lam Si Tung Ho, Duy Nguyen, Binh T. Nguyen
Abstract	We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails. To enable such analyses, we introduce two new conditions: (i) the envelope function $\sup_{f \in \mathcal{F}}\ell \circ f$, where $\ell$ is the loss function and $\mathcal{F}$ is the hypothesis class, exists and is $L^r$-integrable, and (ii) $\ell$ satisfies the multi-scale Bernstein’s condition on $\mathcal{F}$. Under these assumptions, we prove that learning rate faster than $O(n^{-1/2})$ can be obtained and, depending on $r$ and the multi-scale Bernstein’s powers, can be arbitrarily close to $O(n^{-1})$. We then verify these assumptions and derive fast learning rates for the problem of vector quantization by $k$-means clustering with heavy-tailed distributions. The analyses enable us to obtain novel learning rates that extend and complement existing results in the literature from both theoretical and practical viewpoints.
Tasks	Quantization
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09481v1
PDF	http://arxiv.org/pdf/1609.09481v1.pdf
PWC	https://paperswithcode.com/paper/fast-learning-rates-with-heavy-tailed-losses
Repo
Framework

Label distribution based facial attractiveness computation by deep residual learning


Title	Label distribution based facial attractiveness computation by deep residual learning
Authors	Shu Liu, Bo Li, Yangyu Fan, Zhe Guo, Ashok Samal
Abstract	Two challenges lie in the facial attractiveness computation research: the lack of true attractiveness labels (scores), and the lack of an accurate face representation. In order to address the first challenge, this paper recasts facial attractiveness computation as a label distribution learning (LDL) problem rather than a traditional single-label supervised learning task. In this way, the negative influence of the label incomplete problem can be reduced. Inspired by the recent promising work in face recognition using deep neural networks to learn effective features, the second challenge is expected to be solved from a deep learning point of view. A very deep residual network is utilized to enable automatic learning of hierarchical aesthetics representation. Integrating these two ideas, an end-to-end deep learning framework is established. Our approach achieves the best results on a standard benchmark SCUT-FBP dataset compared with other state-of-the-art work.
Tasks	Face Recognition
Published	2016-09-02
URL	http://arxiv.org/abs/1609.00496v2
PDF	http://arxiv.org/pdf/1609.00496v2.pdf
PWC	https://paperswithcode.com/paper/label-distribution-based-facial
Repo
Framework

The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks


Title	The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks
Authors	Babak Saleh, Ahmed Elgammal, Jacob Feldman
Abstract	Deep artificial neural networks have made remarkable progress in different tasks in the field of computer vision. However, the empirical analysis of these models and investigation of their failure cases has received attention recently. In this work, we show that deep learning models cannot generalize to atypical images that are substantially different from training images. This is in contrast to the superior generalization ability of the visual system in the human brain. We focus on Convolutional Neural Networks (CNN) as the state-of-the-art models in object recognition and classification; investigate this problem in more detail, and hypothesize that training CNN models suffer from unstructured loss minimization. We propose computational models to improve the generalization capacity of CNNs by considering how typical a training image looks like. By conducting an extensive set of experiments we show that involving a typicality measure can improve the classification results on a new set of images by a large margin. More importantly, this significant improvement is achieved without fine-tuning the CNN model on the target image set.
Tasks	Object Classification, Object Recognition
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02865v1
PDF	http://arxiv.org/pdf/1602.02865v1.pdf
PWC	https://paperswithcode.com/paper/the-role-of-typicality-in-object
Repo
Framework