May 5, 2019

2942 words 14 mins read

Paper Group ANR 452

Localized Dictionary design for Geometrically Robust Sonar ATR. Pooling Faces: Template based Face Recognition with Pooled Face Images. Grid Loss: Detecting Occluded Faces. Benefits of depth in neural networks. Do semantic parts emerge in Convolutional Neural Networks?. Sparse model selection in the highly under-sampled regime. On Differentiating P …

Localized Dictionary design for Geometrically Robust Sonar ATR


Title	Localized Dictionary design for Geometrically Robust Sonar ATR
Authors	John McKay, Vishal Monga, Raghu Raj
Abstract	Advancements in Sonar image capture have opened the door to powerful classification schemes for automatic target recognition (ATR. Recent work has particularly seen the application of sparse reconstruction-based classification (SRC) to sonar ATR, which provides compelling accuracy rates even in the presence of noise and blur. Existing sparsity based sonar ATR techniques however assume that the test images exhibit geometric pose that is consistent with respect to the training set. This work addresses the outstanding open challenge of handling inconsistently posed test sonar images relative to training. We develop a new localized block-based dictionary design that can enable geometric, i.e. pose robustness. Further, a dictionary learning method is incorporated to increase performance and efficiency. The proposed SRC with Localized Pose Management (LPM), is shown to outperform the state of the art SIFT feature and SVM approach, due to its power to discern background clutter in Sonar images.
Tasks	Dictionary Learning
Published	2016-01-13
URL	http://arxiv.org/abs/1601.03323v1
PDF	http://arxiv.org/pdf/1601.03323v1.pdf
PWC	https://paperswithcode.com/paper/localized-dictionary-design-for-geometrically
Repo
Framework

Pooling Faces: Template based Face Recognition with Pooled Face Images


Title	Pooling Faces: Template based Face Recognition with Pooled Face Images
Authors	Tal Hassner, Iacopo Masi, Jungyeon Kim, Jongmoo Choi, Shai Harel, Prem Natarajan, Gerard Medioni
Abstract	We propose a novel approach to template based face recognition. Our dual goal is to both increase recognition accuracy and reduce the computational and storage costs of template matching. To do this, we leverage on an approach which was proven effective in many other domains, but, to our knowledge, never fully explored for face images: average pooling of face photos. We show how (and why!) the space of a template’s images can be partitioned and then pooled based on image quality and head pose and the effect this has on accuracy and template size. We perform extensive tests on the IJB-A and Janus CS2 template based face identification and verification benchmarks. These show that not only does our approach outperform published state of the art despite requiring far fewer cross template comparisons, but also, surprisingly, that image pooling performs on par with deep feature pooling.
Tasks	Face Identification, Face Recognition
Published	2016-07-06
URL	http://arxiv.org/abs/1607.01450v1
PDF	http://arxiv.org/pdf/1607.01450v1.pdf
PWC	https://paperswithcode.com/paper/pooling-faces-template-based-face-recognition
Repo
Framework

Grid Loss: Detecting Occluded Faces


Title	Grid Loss: Detecting Occluded Faces
Authors	Michael Opitz, Georg Waltner, Georg Poier, Horst Possegger, Horst Bischof
Abstract	Detection of partially occluded objects is a challenging computer vision problem. Standard Convolutional Neural Network (CNN) detectors fail if parts of the detection window are occluded, since not every sub-part of the window is discriminative on its own. To address this issue, we propose a novel loss layer for CNNs, named grid loss, which minimizes the error rate on sub-blocks of a convolution layer independently rather than over the whole feature map. This results in parts being more discriminative on their own, enabling the detector to recover if the detection window is partially occluded. By mapping our loss layer back to a regular fully connected layer, no additional computational cost is incurred at runtime compared to standard CNNs. We demonstrate our method for face detection on several public face detection benchmarks and show that our method outperforms regular CNNs, is suitable for realtime applications and achieves state-of-the-art performance.
Tasks	Face Detection
Published	2016-09-01
URL	http://arxiv.org/abs/1609.00129v1
PDF	http://arxiv.org/pdf/1609.00129v1.pdf
PWC	https://paperswithcode.com/paper/grid-loss-detecting-occluded-faces
Repo
Framework

Benefits of depth in neural networks


Title	Benefits of depth in neural networks
Authors	Matus Telgarsky
Abstract	For any positive integer $k$, there exist neural networks with $\Theta(k^3)$ layers, $\Theta(1)$ nodes per layer, and $\Theta(1)$ distinct parameters which can not be approximated by networks with $\mathcal{O}(k)$ layers unless they are exponentially large — they must possess $\Omega(2^k)$ nodes. This result is proved here for a class of nodes termed “semi-algebraic gates” which includes the common choices of ReLU, maximum, indicator, and piecewise polynomial functions, therefore establishing benefits of depth against not just standard networks with ReLU gates, but also convolutional networks with ReLU and maximization gates, sum-product networks, and boosted decision trees (in this last case with a stronger separation: $\Omega(2^{k^3})$ total tree nodes are required).
Tasks
Published	2016-02-14
URL	http://arxiv.org/abs/1602.04485v2
PDF	http://arxiv.org/pdf/1602.04485v2.pdf
PWC	https://paperswithcode.com/paper/benefits-of-depth-in-neural-networks
Repo
Framework

Do semantic parts emerge in Convolutional Neural Networks?


Title	Do semantic parts emerge in Convolutional Neural Networks?
Authors	Abel Gonzalez-Garcia, Davide Modolo, Vittorio Ferrari
Abstract	Semantic object parts can be useful for several visual recognition tasks. Lately, these tasks have been addressed using Convolutional Neural Networks (CNN), achieving outstanding results. In this work we study whether CNNs learn semantic parts in their internal representation. We investigate the responses of convolutional filters and try to associate their stimuli with semantic parts. We perform two extensive quantitative analyses. First, we use ground-truth part bounding-boxes from the PASCAL-Part dataset to determine how many of those semantic parts emerge in the CNN. We explore this emergence for different layers, network depths, and supervision levels. Second, we collect human judgements in order to study what fraction of all filters systematically fire on any semantic part, even if not annotated in PASCAL-Part. Moreover, we explore several connections between discriminative power and semantics. We find out which are the most discriminative filters for object recognition, and analyze whether they respond to semantic parts or to other image patches. We also investigate the other direction: we determine which semantic parts are the most discriminative and whether they correspond to those parts emerging in the network. This enables to gain an even deeper understanding of the role of semantic parts in the network.
Tasks	Object Recognition
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03738v5
PDF	http://arxiv.org/pdf/1607.03738v5.pdf
PWC	https://paperswithcode.com/paper/do-semantic-parts-emerge-in-convolutional
Repo
Framework

Sparse model selection in the highly under-sampled regime


Title	Sparse model selection in the highly under-sampled regime
Authors	Nicola Bulso, Matteo Marsili, Yasser Roudi
Abstract	We propose a method for recovering the structure of a sparse undirected graphical model when very few samples are available. The method decides about the presence or absence of bonds between pairs of variable by considering one pair at a time and using a closed form formula, analytically derived by calculating the posterior probability for every possible model explaining a two body system using Jeffreys prior. The approach does not rely on the optimisation of any cost functions and consequently is much faster than existing algorithms. Despite this time and computational advantage, numerical results show that for several sparse topologies the algorithm is comparable to the best existing algorithms, and is more accurate in the presence of hidden variables. We apply this approach to the analysis of US stock market data and to neural data, in order to show its efficiency in recovering robust statistical dependencies in real data with non stationary correlations in time and space.
Tasks	Model Selection
Published	2016-03-03
URL	http://arxiv.org/abs/1603.00952v2
PDF	http://arxiv.org/pdf/1603.00952v2.pdf
PWC	https://paperswithcode.com/paper/sparse-model-selection-in-the-highly-under
Repo
Framework

On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization


Title	On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
Authors	Stephen Gould, Basura Fernando, Anoop Cherian, Peter Anderson, Rodrigo Santa Cruz, Edison Guo
Abstract	Some recent works in machine learning and computer vision involve the solution of a bi-level optimization problem. Here the solution of a parameterized lower-level problem binds variables that appear in the objective of an upper-level problem. The lower-level problem typically appears as an argmin or argmax optimization problem. Many techniques have been proposed to solve bi-level optimization problems, including gradient descent, which is popular with current end-to-end learning approaches. In this technical report we collect some results on differentiating argmin and argmax optimization problems with and without constraints and provide some insightful motivating examples.
Tasks
Published	2016-07-19
URL	http://arxiv.org/abs/1607.05447v2
PDF	http://arxiv.org/pdf/1607.05447v2.pdf
PWC	https://paperswithcode.com/paper/on-differentiating-parameterized-argmin-and
Repo
Framework

Automatic Data Deformation Analysis on Evolving Folksonomy Driven Environment


Title	Automatic Data Deformation Analysis on Evolving Folksonomy Driven Environment
Authors	Massimiliano Dal Mas
Abstract	The Folksodriven framework makes it possible for data scientists to define an ontology environment where searching for buried patterns that have some kind of predictive power to build predictive models more effectively. It accomplishes this through an abstractions that isolate parameters of the predictive modeling process searching for patterns and designing the feature set, too. To reflect the evolving knowledge, this paper considers ontologies based on folksonomies according to a new concept structure called “Folksodriven” to represent folksonomies. So, the studies on the transformational regulation of the Folksodriven tags are regarded to be important for adaptive folksonomies classifications in an evolving environment used by Intelligent Systems to represent the knowledge sharing. Folksodriven tags are used to categorize salient data points so they can be fed to a machine-learning system and “featurizing” the data.
Tasks
Published	2016-12-30
URL	http://arxiv.org/abs/1612.09574v1
PDF	http://arxiv.org/pdf/1612.09574v1.pdf
PWC	https://paperswithcode.com/paper/automatic-data-deformation-analysis-on
Repo
Framework

Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problem


Title	Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problem
Authors	Peng Guo, Wenming Cheng, Yi Wang
Abstract	This paper considers the two-stage capacitated facility location problem (TSCFLP) in which products manufactured in plants are delivered to customers via storage depots. Customer demands are satisfied subject to limited plant production and limited depot storage capacity. The objective is to determine the locations of plants and depots in order to minimize the total cost including the fixed cost and transportation cost. A hybrid evolutionary algorithm (HEA) with genetic operations and local search is proposed. To avoid the expensive calculation of fitness of population in terms of computational time, the HEA uses extreme machine learning to approximate the fitness of most of the individuals. Moreover, two heuristics based on the characteristic of the problem is incorporated to generate a good initial population. Computational experiments are performed on two sets of test instances from the recent literature. The performance of the proposed algorithm is evaluated and analyzed. Compared with the state-of-the-art genetic algorithm, the proposed algorithm can find the optimal or near-optimal solutions in a reasonable computational time.
Tasks
Published	2016-05-22
URL	http://arxiv.org/abs/1605.06722v1
PDF	http://arxiv.org/pdf/1605.06722v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-evolutionary-algorithm-with-extreme
Repo
Framework

Ordonnancement d’entités pour la rencontre du web des documents et du web des données


Title	Ordonnancement d’entités pour la rencontre du web des documents et du web des données
Authors	Mazen Alsarem, Pierre-Edouard Portier, Sylvie Calabretto, Harald Kosch
Abstract	The advances of the Linked Open Data (LOD) initiative are giving rise to a more structured web of data. Indeed, a few datasets act as hubs (e.g., DBpedia) connecting many other datasets. They also made possible new web services for entity detection inside plain text (e.g., DBpedia Spotlight), thus allowing for new applications that will benefit from a combination of the web of documents and the web of data. To ease the emergence of these new use-cases, we propose a query-biased algorithm for the ranking of entities detected inside a web page. Our algorithm combine link analysis with dimensionality reduction. We use crowdsourcing for building a publicly available and reusable dataset on which we compare our algorithm to the state of the art. Finally, we use this algorithm for the construction of semantic snippets for which we evaluate the usability and the usefulness with a crowdsourcing-based approach.
Tasks	Dimensionality Reduction
Published	2016-02-19
URL	http://arxiv.org/abs/1602.06136v1
PDF	http://arxiv.org/pdf/1602.06136v1.pdf
PWC	https://paperswithcode.com/paper/ordonnancement-dentites-pour-la-rencontre-du
Repo
Framework

Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning


Title	Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning
Authors	Niloofar Yousefi, Yunwen Lei, Marius Kloft, Mansooreh Mollaghasemi, Georgios Anagnostopoulos
Abstract	We show a Talagrand-type concentration inequality for Multi-Task Learning (MTL), using which we establish sharp excess risk bounds for MTL in terms of distribution- and data-dependent versions of the Local Rademacher Complexity (LRC). We also give a new bound on the LRC for norm regularized as well as strongly convex hypothesis classes, which applies not only to MTL but also to the standard i.i.d. setting. Combining both results, one can now easily derive fast-rate bounds on the excess risk for many prominent MTL methods, including—as we demonstrate—Schatten-norm, group-norm, and graph-regularized MTL. The derived bounds reflect a relationship akeen to a conservation law of asymptotic convergence rates. This very relationship allows for trading off slower rates w.r.t. the number of tasks for faster rates with respect to the number of available samples per task, when compared to the rates obtained via a traditional, global Rademacher analysis.
Tasks	Multi-Task Learning
Published	2016-02-18
URL	http://arxiv.org/abs/1602.05916v2
PDF	http://arxiv.org/pdf/1602.05916v2.pdf
PWC	https://paperswithcode.com/paper/local-rademacher-complexity-based-learning
Repo
Framework

Unraveling reported dreams with text analytics


Title	Unraveling reported dreams with text analytics
Authors	Iris Hendrickx, Louis Onrust, Florian Kunneman, Ali Hürriyetoğlu, Antal van den Bosch, Wessel Stoop
Abstract	We investigate what distinguishes reported dreams from other personal narratives. The continuity hypothesis, stemming from psychological dream analysis work, states that most dreams refer to a person’s daily life and personal concerns, similar to other personal narratives such as diary entries. Differences between the two texts may reveal the linguistic markers of dream text, which could be the basis for new dream analysis work and for the automatic detection of dream descriptions. We used three text analytics methods: text classification, topic modeling, and text coherence analysis, and applied these methods to a balanced set of texts representing dreams, diary entries, and other personal stories. We observed that dream texts could be distinguished from other personal narratives nearly perfectly, mostly based on the presence of uncertainty markers and descriptions of scenes. Important markers for non-dream narratives are specific time expressions and conversational expressions. Dream texts also exhibit a lower discourse coherence than other personal narratives.
Tasks	Text Classification
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03659v1
PDF	http://arxiv.org/pdf/1612.03659v1.pdf
PWC	https://paperswithcode.com/paper/unraveling-reported-dreams-with-text
Repo
Framework

A real-time analysis of rock fragmentation using UAV technology


Title	A real-time analysis of rock fragmentation using UAV technology
Authors	Thomas Bamford, Kamran Esmaeili, Angela P. Schoellig
Abstract	Accurate measurement of blast-induced rock fragmentation is of great importance for many mining operations. The post-blast rock size distribution can significantly influence the efficiency of all the downstream mining and comminution processes. Image analysis methods are one of the most common methods used to measure rock fragment size distribution in mines regardless of criticism for lack of accuracy to measure fine particles and other perceived deficiencies. The current practice of collecting rock fragmentation data for image analysis is highly manual and provides data with low temporal and spatial resolution. Using UAVs for collecting images of rock fragments can not only improve the quality of the image data but also automate the data collection process. Ultimately, real-time acquisition of high temporal- and spatial-resolution data based on UAV technology will provide a broad range of opportunities for both improving blast design without interrupting the production process and reducing the cost of the human operator. This paper presents the results of a series of laboratory-scale rock fragment measurements using a quadrotor UAV equipped with a camera. The goal of this work is to highlight the benefits of aerial fragmentation analysis in terms of both prediction accuracy and time effort. A pile of rock fragments with different fragment sizes was placed in a lab that is equipped with a motion capture camera system for precise UAV localization and control. Such an environment presents optimal conditions for UAV flight and thus, is well-suited for conducting proof-of-concept experiments before testing them in large-scale field experiments. The pile was photographed by a camera attached to the UAV, and the particle size distribution curves were generated in almost real-time. The pile was also manually photographed and the results of the manual method were compared to the UAV method.
Tasks	Motion Capture
Published	2016-07-14
URL	http://arxiv.org/abs/1607.04243v1
PDF	http://arxiv.org/pdf/1607.04243v1.pdf
PWC	https://paperswithcode.com/paper/a-real-time-analysis-of-rock-fragmentation
Repo
Framework

Simulation of an Optional Strategy in the Prisoner’s Dilemma in Spatial and Non-spatial Environments


Title	Simulation of an Optional Strategy in the Prisoner’s Dilemma in Spatial and Non-spatial Environments
Authors	Marcos Cardinot, Maud Gibbons, Colm O’Riordan, Josephine Griffith
Abstract	This paper presents research comparing the effects of different environments on the outcome of an extended Prisoner’s Dilemma, in which agents have the option to abstain from playing the game. We consider three different pure strategies: cooperation, defection and abstinence. We adopt an evolutionary game theoretic approach and consider two different environments: the first which imposes no spatial constraints and the second in which agents are placed on a lattice grid. We analyse the performance of the three strategies as we vary the loner’s payoff in both structured and unstructured environments. Furthermore we also present the results of simulations which identify scenarios in which cooperative clusters of agents emerge and persist in both environments.
Tasks
Published	2016-08-17
URL	http://arxiv.org/abs/1608.05044v1
PDF	http://arxiv.org/pdf/1608.05044v1.pdf
PWC	https://paperswithcode.com/paper/simulation-of-an-optional-strategy-in-the
Repo
Framework

Stochastic Matrix Factorization


Title	Stochastic Matrix Factorization
Authors	Christopher Adams
Abstract	This paper considers a restriction to non-negative matrix factorization in which at least one matrix factor is stochastic. That is, the elements of the matrix factors are non-negative and the columns of one matrix factor sum to 1. This restriction includes topic models, a popular method for analyzing unstructured data. It also includes a method for storing and finding pictures. The paper presents necessary and sufficient conditions on the observed data such that the factorization is unique. In addition, the paper characterizes natural bounds on the parameters for any observed data and presents a consistent least squares estimator. The results are illustrated using a topic model analysis of PhD abstracts in economics and the problem of storing and retrieving a set of pictures of faces.
Tasks	Topic Models
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05772v1
PDF	http://arxiv.org/pdf/1609.05772v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-matrix-factorization
Repo
Framework