May 6, 2019

3197 words 16 mins read

Paper Group ANR 340

Multi-Scale Anisotropic Fourth-Order Diffusion Improves Ridge and Valley Localization. User Personalized Satisfaction Prediction via Multiple Instance Deep Learning. Context Trees: Augmenting Geospatial Trajectories with Context. New version of Gram-Schmidt Process with inverse for Signal and Image Processing. Efficiency of active learning for the …

Multi-Scale Anisotropic Fourth-Order Diffusion Improves Ridge and Valley Localization


Title	Multi-Scale Anisotropic Fourth-Order Diffusion Improves Ridge and Valley Localization
Authors	Shekoufeh Gorgi Zadeh, Stephan Didas, Maximilian W. M. Wintergerst, Thomas Schultz
Abstract	Ridge and valley enhancing filters are widely used in applications such as vessel detection in medical image computing. When images are degraded by noise or include vessels at different scales, such filters are an essential step for meaningful and stable vessel localization. In this work, we propose a novel multi-scale anisotropic fourth-order diffusion equation that allows us to smooth along vessels, while sharpening them in the orthogonal direction. The proposed filter uses a fourth order diffusion tensor whose eigentensors and eigenvalues are determined from the local Hessian matrix, at a scale that is automatically selected for each pixel. We discuss efficient implementation using a Fast Explicit Diffusion scheme and demonstrate results on synthetic images and vessels in fundus images. Compared to previous isotropic and anisotropic fourth-order filters, as well as established second-order vessel enhancing filters, our newly proposed one better restores the centerlines in all cases.
Tasks
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06906v2
PDF	http://arxiv.org/pdf/1611.06906v2.pdf
PWC	https://paperswithcode.com/paper/multi-scale-anisotropic-fourth-order
Repo
Framework

User Personalized Satisfaction Prediction via Multiple Instance Deep Learning


Title	User Personalized Satisfaction Prediction via Multiple Instance Deep Learning
Authors	Zheqian Chen, Ben Gao, Huimin Zhang, Zhou Zhao, Deng Cai
Abstract	Community based question answering services have arisen as a popular knowledge sharing pattern for netizens. With abundant interactions among users, individuals are capable of obtaining satisfactory information. However, it is not effective for users to attain answers within minutes. Users have to check the progress over time until the satisfying answers submitted. We address this problem as a user personalized satisfaction prediction task. Existing methods usually exploit manual feature selection. It is not desirable as it requires careful design and is labor intensive. In this paper, we settle this issue by developing a new multiple instance deep learning framework. Specifically, in our settings, each question follows a weakly supervised learning multiple instance learning assumption, where its obtained answers can be regarded as instance sets and we define the question resolved with at least one satisfactory answer. We thus design an efficient framework exploiting multiple instance learning property with deep learning to model the question answer pairs. Extensive experiments on large scale datasets from Stack Exchange demonstrate the feasibility of our proposed framework in predicting askers personalized satisfaction. Our framework can be extended to numerous applications such as UI satisfaction Prediction, multi armed bandit problem, expert finding and so on.
Tasks	Feature Selection, Multiple Instance Learning, Question Answering
Published	2016-11-24
URL	http://arxiv.org/abs/1611.08096v1
PDF	http://arxiv.org/pdf/1611.08096v1.pdf
PWC	https://paperswithcode.com/paper/user-personalized-satisfaction-prediction-via
Repo
Framework

Context Trees: Augmenting Geospatial Trajectories with Context


Title	Context Trees: Augmenting Geospatial Trajectories with Context
Authors	Alasdair Thomason, Nathan Griffiths, Victor Sanchez
Abstract	Exposing latent knowledge in geospatial trajectories has the potential to provide a better understanding of the movements of individuals and groups. Motivated by such a desire, this work presents the context tree, a new hierarchical data structure that summarises the context behind user actions in a single model. We propose a method for context tree construction that augments geospatial trajectories with land usage data to identify such contexts. Through evaluation of the construction method and analysis of the properties of generated context trees, we demonstrate the foundation for understanding and modelling behaviour afforded. Summarising user contexts into a single data structure gives easy access to information that would otherwise remain latent, providing the basis for better understanding and predicting the actions and behaviours of individuals and groups. Finally, we also present a method for pruning context trees, for use in applications where it is desirable to reduce the size of the tree while retaining useful information.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04269v1
PDF	http://arxiv.org/pdf/1606.04269v1.pdf
PWC	https://paperswithcode.com/paper/context-trees-augmenting-geospatial
Repo
Framework

New version of Gram-Schmidt Process with inverse for Signal and Image Processing


Title	New version of Gram-Schmidt Process with inverse for Signal and Image Processing
Authors	Mario Mastriani
Abstract	The Gram-Schmidt Process (GSP) is used to convert a non-orthogonal basis (a set of linearly independent vectors, matrices, etc) into an orthonormal basis (a set of orthogonal, unit-length vectors, bi or tri dimensional matrices). The process consists of taking each array and then subtracting the projections in common with the previous arrays. This paper introduces an enhanced version of the Gram-Schmidt Process (EGSP) with inverse, which is useful for Digital Signal and Image Processing, among others applications.
Tasks
Published	2016-07-16
URL	http://arxiv.org/abs/1607.04759v1
PDF	http://arxiv.org/pdf/1607.04759v1.pdf
PWC	https://paperswithcode.com/paper/new-version-of-gram-schmidt-process-with
Repo
Framework

Efficiency of active learning for the allocation of workers on crowdsourced classification tasks


Title	Efficiency of active learning for the allocation of workers on crowdsourced classification tasks
Authors	Edoardo Manino, Long Tran-Thanh, Nicholas R. Jennings
Abstract	Crowdsourcing has been successfully employed in the past as an effective and cheap way to execute classification tasks and has therefore attracted the attention of the research community. However, we still lack a theoretical understanding of how to collect the labels from the crowd in an optimal way. In this paper we focus on the problem of worker allocation and compare two active learning policies proposed in the empirical literature with a uniform allocation of the available budget. To this end we make a thorough mathematical analysis of the problem and derive a new bound on the performance of the system. Furthermore we run extensive simulations in a more realistic scenario and show that our theoretical results hold in practice.
Tasks	Active Learning
Published	2016-10-19
URL	http://arxiv.org/abs/1610.06106v1
PDF	http://arxiv.org/pdf/1610.06106v1.pdf
PWC	https://paperswithcode.com/paper/efficiency-of-active-learning-for-the
Repo
Framework

Combining Multiple Cues for Visual Madlibs Question Answering


Title	Combining Multiple Cues for Visual Madlibs Question Answering
Authors	Tatiana Tommasi, Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Alexander C. Berg, Tamara L. Berg
Abstract	This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset. Instead of generic and commonly used representations trained on the ImageNet classification task, our approach employs a combination of networks trained for specialized tasks such as scene recognition, person activity classification, and attribute prediction. We also present a method for localizing phrases from candidate answers in order to provide spatial support for feature extraction. We map each of these features, together with candidate answers, to a joint embedding space through normalized canonical correlation analysis (nCCA). Finally, we solve an optimization problem to learn to combine scores from nCCA models trained on multiple cues to select the best answer. Extensive experimental results show a significant improvement over the previous state of the art and confirm that answering questions from a wide range of types benefits from examining a variety of image cues and carefully choosing the spatial support for feature extraction.
Tasks	Question Answering, Scene Recognition
Published	2016-11-01
URL	http://arxiv.org/abs/1611.00393v3
PDF	http://arxiv.org/pdf/1611.00393v3.pdf
PWC	https://paperswithcode.com/paper/combining-multiple-cues-for-visual-madlibs
Repo
Framework

Uncertainty in Neural Network Word Embedding: Exploration of Threshold for Similarity


Title	Uncertainty in Neural Network Word Embedding: Exploration of Threshold for Similarity
Authors	Navid Rekabsaz, Mihai Lupu, Allan Hanbury
Abstract	Word embedding, specially with its recent developments, promises a quantification of the similarity between terms. However, it is not clear to which extent this similarity value can be genuinely meaningful and useful for subsequent tasks. We explore how the similarity score obtained from the models is really indicative of term relatedness. We first observe and quantify the uncertainty factor of the word embedding models regarding to the similarity value. Based on this factor, we introduce a general threshold on various dimensions which effectively filters the highly related terms. Our evaluation on four information retrieval collections supports the effectiveness of our approach as the results of the introduced threshold are significantly better than the baseline while being equal to or statistically indistinguishable from the optimal results.
Tasks	Information Retrieval
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06086v2
PDF	http://arxiv.org/pdf/1606.06086v2.pdf
PWC	https://paperswithcode.com/paper/uncertainty-in-neural-network-word-embedding
Repo
Framework

Research Project: Text Engineering Tool for Ontological Scientometry


Title	Research Project: Text Engineering Tool for Ontological Scientometry
Authors	Rustam Tagiew
Abstract	The number of scientific papers grows exponentially in many disciplines. The share of online available papers grows as well. At the same time, the period of time for a paper to loose at chance to be cited anymore shortens. The decay of the citing rate shows similarity to ultradiffusional processes as for other online contents in social networks. The distribution of papers per author shows similarity to the distribution of posts per user in social networks. The rate of uncited papers for online available papers grows while some papers ‘go viral’ in terms of being cited. Summarized, the practice of scientific publishing moves towards the domain of social networks. The goal of this project is to create a text engineering tool, which can semi-automatically categorize a paper according to its type of contribution and extract relationships between them into an ontological database. Semi-automatic categorization means that the mistakes made by automatic pre-categorization and relationship-extraction will be corrected through a wikipedia-like front-end by volunteers from general public. This tool should not only help researchers and the general public to find relevant supplementary material and peers faster, but also provide more information for research funding agencies.
Tasks	Relationship Extraction (Distant Supervised)
Published	2016-01-08
URL	http://arxiv.org/abs/1601.01887v1
PDF	http://arxiv.org/pdf/1601.01887v1.pdf
PWC	https://paperswithcode.com/paper/research-project-text-engineering-tool-for
Repo
Framework

Heavy hitters via cluster-preserving clustering


Title	Heavy hitters via cluster-preserving clustering
Authors	Kasper Green Larsen, Jelani Nelson, Huy L. Nguyen, Mikkel Thorup
Abstract	In turnstile $\ell_p$ $\varepsilon$-heavy hitters, one maintains a high-dimensional $x\in\mathbb{R}^n$ subject to $\texttt{update}(i,\Delta)$ causing $x_i\leftarrow x_i + \Delta$, where $i\in[n]$, $\Delta\in\mathbb{R}$. Upon receiving a query, the goal is to report a small list $L\subset[n]$, $L = O(1/\varepsilon^p)$, containing every “heavy hitter” $i\in[n]$ with $x_i \ge \varepsilon \x_{\overline{1/\varepsilon^p}}_p$, where $x_{\overline{k}}$ denotes the vector obtained by zeroing out the largest $k$ entries of $x$ in magnitude. For any $p\in(0,2]$ the CountSketch solves $\ell_p$ heavy hitters using $O(\varepsilon^{-p}\log n)$ words of space with $O(\log n)$ update time, $O(n\log n)$ query time to output $L$, and whose output after any query is correct with high probability (whp) $1 - 1/poly(n)$. Unfortunately the query time is very slow. To remedy this, the work [CM05] proposed for $p=1$ in the strict turnstile model, a whp correct algorithm achieving suboptimal space $O(\varepsilon^{-1}\log^2 n)$, worse update time $O(\log^2 n)$, but much better query time $O(\varepsilon^{-1}poly(\log n))$. We show this tradeoff between space and update time versus query time is unnecessary. We provide a new algorithm, ExpanderSketch, which in the most general turnstile model achieves optimal $O(\varepsilon^{-p}\log n)$ space, $O(\log n)$ update time, and fast $O(\varepsilon^{-p}poly(\log n))$ query time, and whp correctness. Our main innovation is an efficient reduction from the heavy hitters to a clustering problem in which each heavy hitter is encoded as some form of noisy spectral cluster in a much bigger graph, and the goal is to identify every cluster. Since every heavy hitter must be found, correctness requires that every cluster be found. We then develop a “cluster-preserving clustering” algorithm, partitioning the graph into clusters without destroying any original cluster.
Tasks
Published	2016-04-05
URL	http://arxiv.org/abs/1604.01357v1
PDF	http://arxiv.org/pdf/1604.01357v1.pdf
PWC	https://paperswithcode.com/paper/heavy-hitters-via-cluster-preserving
Repo
Framework

A regularization-based approach for unsupervised image segmentation


Title	A regularization-based approach for unsupervised image segmentation
Authors	Aleksandar Dimitriev, Matej Kristan
Abstract	We propose a novel unsupervised image segmentation algorithm, which aims to segment an image into several coherent parts. It requires no user input, no supervised learning phase and assumes an unknown number of segments. It achieves this by first over-segmenting the image into several hundred superpixels. These are iteratively joined on the basis of a discriminative classifier trained on color and texture information obtained from each superpixel. The output of the classifier is regularized by a Markov random field that lends more influence to neighbouring superpixels that are more similar. In each iteration, similar superpixels fall under the same label, until only a few coherent regions remain in the image. The algorithm was tested on a standard evaluation data set, where it performs on par with state-of-the-art algorithms in term of precision and greatly outperforms the state of the art by reducing the oversegmentation of the object of interest.
Tasks	Semantic Segmentation
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02649v1
PDF	http://arxiv.org/pdf/1603.02649v1.pdf
PWC	https://paperswithcode.com/paper/a-regularization-based-approach-for
Repo
Framework

Places: An Image Database for Deep Scene Understanding


Title	Places: An Image Database for Deep Scene Understanding
Authors	Bolei Zhou, Aditya Khosla, Agata Lapedriza, Antonio Torralba, Aude Oliva
Abstract	The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification at tasks such as object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories and attributes, comprising a quasi-exhaustive list of the types of environments encountered in the world. Using state of the art Convolutional Neural Networks, we provide impressive baseline performances at scene classification. With its high-coverage and high-diversity of exemplars, the Places Database offers an ecosystem to guide future progress on currently intractable visual recognition problems.
Tasks	Scene Classification, Scene Recognition, Scene Understanding
Published	2016-10-06
URL	http://arxiv.org/abs/1610.02055v1
PDF	http://arxiv.org/pdf/1610.02055v1.pdf
PWC	https://paperswithcode.com/paper/places-an-image-database-for-deep-scene
Repo
Framework

Retrieving sinusoids from nonuniformly sampled data using recursive formulation


Title	Retrieving sinusoids from nonuniformly sampled data using recursive formulation
Authors	Ivan Maric
Abstract	A heuristic procedure based on novel recursive formulation of sinusoid (RFS) and on regression with predictive least-squares (LS) enables to decompose both uniformly and nonuniformly sampled 1-d signals into a sparse set of sinusoids (SSS). An optimal SSS is found by Levenberg-Marquardt (LM) optimization of RFS parameters of near-optimal sinusoids combined with common criteria for the estimation of the number of sinusoids embedded in noise. The procedure estimates both the cardinality and the parameters of SSS. The proposed algorithm enables to identify the RFS parameters of a sinusoid from a data sequence containing only a fraction of its cycle. In extreme cases when the frequency of a sinusoid approaches zero the algorithm is able to detect a linear trend in data. Also, an irregular sampling pattern enables the algorithm to correctly reconstruct the under-sampled sinusoid. Parsimonious nature of the obtaining models opens the possibilities of using the proposed method in machine learning and in expert and intelligent systems needing analysis and simple representation of 1-d signals. The properties of the proposed algorithm are evaluated on examples of irregularly sampled artificial signals in noise and are compared with high accuracy frequency estimation algorithms based on linear prediction (LP) approach, particularly with respect to Cramer-Rao Bound (CRB).
Tasks
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04599v2
PDF	http://arxiv.org/pdf/1612.04599v2.pdf
PWC	https://paperswithcode.com/paper/retrieving-sinusoids-from-nonuniformly
Repo
Framework

Reflectance Adaptive Filtering Improves Intrinsic Image Estimation


Title	Reflectance Adaptive Filtering Improves Intrinsic Image Estimation
Authors	Thomas Nestmeyer, Peter V. Gehler
Abstract	Separating an image into reflectance and shading layers poses a challenge for learning approaches because no large corpus of precise and realistic ground truth decompositions exists. The Intrinsic Images in the Wild~(IIW) dataset provides a sparse set of relative human reflectance judgments, which serves as a standard benchmark for intrinsic images. A number of methods use IIW to learn statistical dependencies between the images and their reflectance layer. Although learning plays an important role for high performance, we show that a standard signal processing technique achieves performance on par with current state-of-the-art. We propose a loss function for CNN learning of dense reflectance predictions. Our results show a simple pixel-wise decision, without any context or prior knowledge, is sufficient to provide a strong baseline on IIW. This sets a competitive baseline which only two other approaches surpass. We then develop a joint bilateral filtering method that implements strong prior knowledge about reflectance constancy. This filtering operation can be applied to any intrinsic image algorithm and we improve several previous results achieving a new state-of-the-art on IIW. Our findings suggest that the effect of learning-based approaches may have been over-estimated so far. Explicit prior knowledge is still at least as important to obtain high performance in intrinsic image decompositions.
Tasks
Published	2016-12-15
URL	http://arxiv.org/abs/1612.05062v2
PDF	http://arxiv.org/pdf/1612.05062v2.pdf
PWC	https://paperswithcode.com/paper/reflectance-adaptive-filtering-improves
Repo
Framework

Contextual object categorization with energy-based model


Title	Contextual object categorization with energy-based model
Authors	Changyong Ri, Duho Pak, Cholryong Choe, Suhyang Kim, Yonghak Sin
Abstract	Object categorization is a hot issue of an image mining. Contextual information between objects is one of the important semantic knowledge of an image. However, the previous researches for an object categorization have not made full use of the contextual information, especially the spatial relations between objects. In addition, the object categorization methods, which generally use the probabilistic graphical models to implement the incorporation of contextual information with appearance of objects, are almost inevitable to evaluate the intractable partition function for normalization. In this work, we introduced fully-connected fuzzy spatial relations including directional, distance and topological relations between object regions, so the spatial relational information could be fully utilized. Then, the spatial relations were considered as well as co-occurrence and appearance of objects by using energy-based model, where the energy function was defined as the region-object association potential and the configuration potential of objects. Minimizing the energy function of whole image arrangement, we obtained the optimal label set about the image regions and addressed the evaluation of intractable partition function in conditional random fields. Experimental results show the validity and reliability of this proposed method.
Tasks
Published	2016-04-23
URL	http://arxiv.org/abs/1604.06852v1
PDF	http://arxiv.org/pdf/1604.06852v1.pdf
PWC	https://paperswithcode.com/paper/contextual-object-categorization-with-energy
Repo
Framework

Sooner than Expected: Hitting the Wall of Complexity in Evolution


Title	Sooner than Expected: Hitting the Wall of Complexity in Evolution
Authors	Thomas Schmickl, Payam Zahadat, Heiko Hamann
Abstract	In evolutionary robotics an encoding of the control software, which maps sensor data (input) to motor control values (output), is shaped by stochastic optimization methods to complete a predefined task. This approach is assumed to be beneficial compared to standard methods of controller design in those cases where no a-priori model is available that could help to optimize performance. Also for robots that have to operate in unpredictable environments, an evolutionary robotics approach is favorable. We demonstrate here that such a model-free approach is not a free lunch, as already simple tasks can represent unsolvable barriers for fully open-ended uninformed evolutionary computation techniques. We propose here the ‘Wankelmut’ task as an objective for an evolutionary approach that starts from scratch without pre-shaped controller software or any other informed approach that would force the behavior to be evolved in a desired way. Our focal claim is that ‘Wankelmut’ represents the simplest set of problems that makes plain-vanilla evolutionary computation fail. We demonstrate this by a series of simple standard evolutionary approaches using different fitness functions and standard artificial neural networks as well as continuous-time recurrent neural networks. All our tested approaches failed. We claim that any other evolutionary approach will also fail that does per-se not favor or enforce modularity and does not freeze or protect already evolved functionalities. Thus we propose a hard-to-pass benchmark and make a strong statement for self-complexifying and generative approaches in evolutionary computation. We anticipate that defining such a ‘simplest task to fail’ is a valuable benchmark for promoting future development in the field of artificial intelligence, evolutionary robotics and artificial life.
Tasks	Artificial Life, Stochastic Optimization
Published	2016-09-25
URL	http://arxiv.org/abs/1609.07722v1
PDF	http://arxiv.org/pdf/1609.07722v1.pdf
PWC	https://paperswithcode.com/paper/sooner-than-expected-hitting-the-wall-of
Repo
Framework