July 26, 2019

3057 words 15 mins read

Paper Group ANR 787

Stereo Matching With Color-Weighted Correlation, Hierarchical Belief Propagation And Occlusion Handling. Discovering Reliable Approximate Functional Dependencies. Real-time Geometry-Aware Augmented Reality in Minimally Invasive Surgery. A Correction Method of a Binary Classifier Applied to Multi-label Pairwise Models. Communicative Capital for Pros …

Stereo Matching With Color-Weighted Correlation, Hierarchical Belief Propagation And Occlusion Handling


Title	Stereo Matching With Color-Weighted Correlation, Hierarchical Belief Propagation And Occlusion Handling
Authors	Vamshhi Pavan Kumar Varma Vegeshna
Abstract	In this paper, we contrive a stereo matching algorithm with careful handling of disparity, discontinuity and occlusion. This algorithm works a worldwide matching stereo model which is based on minimization of energy. The global energy comprises two terms, firstly the data term and secondly the smoothness term. The data term is approximated by a color-weighted correlation, then refined in obstruct and low-texture areas in many applications of hierarchical loopy belief propagation algorithm. The results during the experiment are evaluated on the Middlebury data sets, showing that out algorithm is the top performer among all the algorithms listed there
Tasks	Stereo Matching, Stereo Matching Hand
Published	2017-08-26
URL	http://arxiv.org/abs/1708.07987v2
PDF	http://arxiv.org/pdf/1708.07987v2.pdf
PWC	https://paperswithcode.com/paper/stereo-matching-with-color-weighted
Repo
Framework

Discovering Reliable Approximate Functional Dependencies


Title	Discovering Reliable Approximate Functional Dependencies
Authors	Panagiotis Mandros, Mario Boley, Jilles Vreeken
Abstract	Given a database and a target attribute of interest, how can we tell whether there exists a functional, or approximately functional dependence of the target on any set of other attributes in the data? How can we reliably, without bias to sample size or dimensionality, measure the strength of such a dependence? And, how can we efficiently discover the optimal or $\alpha$-approximate top-$k$ dependencies? These are exactly the questions we answer in this paper. As we want to be agnostic on the form of the dependence, we adopt an information-theoretic approach, and construct a reliable, bias correcting score that can be efficiently computed. Moreover, we give an effective optimistic estimator of this score, by which for the first time we can mine the approximate functional dependencies from data with guarantees of optimality. Empirical evaluation shows that the derived score achieves a good bias for variance trade-off, can be used within an efficient discovery algorithm, and indeed discovers meaningful dependencies. Most important, it remains reliable in the face of data sparsity.
Tasks
Published	2017-05-25
URL	http://arxiv.org/abs/1705.09391v2
PDF	http://arxiv.org/pdf/1705.09391v2.pdf
PWC	https://paperswithcode.com/paper/discovering-reliable-approximate-functional
Repo
Framework

Real-time Geometry-Aware Augmented Reality in Minimally Invasive Surgery


Title	Real-time Geometry-Aware Augmented Reality in Minimally Invasive Surgery
Authors	Long Chen, Wen Tang, Nigel W. John
Abstract	The potential of Augmented Reality (AR) technology to assist minimally invasive surgeries (MIS) lies in its computational performance and accuracy in dealing with challenging MIS scenes. Even with the latest hardware and software technologies, achieving both real-time and accurate augmented information overlay in MIS is still a formidable task. In this paper, we present a novel real-time AR framework for MIS that achieves interactive geometric aware augmented reality in endoscopic surgery with stereo views. Our framework tracks the movement of the endoscopic camera and simultaneously reconstructs a dense geometric mesh of the MIS scene. The movement of the camera is predicted by minimising the re-projection error to achieve a fast tracking performance, while the 3D mesh is incrementally built by a dense zero mean normalised cross correlation stereo matching method to improve the accuracy of the surface reconstruction. Our proposed system does not require any prior template or pre-operative scan and can infer the geometric information intra-operatively in real-time. With the geometric information available, our proposed AR framework is able to interactively add annotations, localisation of tumours and vessels, and measurement labelling with greater precision and accuracy compared with the state of the art approaches.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01234v1
PDF	http://arxiv.org/pdf/1708.01234v1.pdf
PWC	https://paperswithcode.com/paper/real-time-geometry-aware-augmented-reality-in
Repo
Framework

A Correction Method of a Binary Classifier Applied to Multi-label Pairwise Models


Title	A Correction Method of a Binary Classifier Applied to Multi-label Pairwise Models
Authors	Pawel Trajdos, Marek Kurzynski
Abstract	In this work, we addressed the issue of applying a stochastic classifier and a local, fuzzy confusion matrix under the framework of multi-label classification. We proposed a novel solution to the problem of correcting label pairwise ensembles. The main step of the correction procedure is to compute classifier- specific competence and cross-competence measures, which estimates error pattern of the underlying classifier. We considered two improvements of the method of obtaining confusion matrices. The first one is aimed to deal with imbalanced labels. The other utilizes double labelled instances which are usually removed during the pairwise transformation. The proposed methods were evaluated using 29 benchmark datasets. In order to assess the efficiency of the introduced models, they were compared against 1 state-of-the-art approach and the correction scheme based on the original method of confusion matrix estimation. The comparison was performed using four different multi-label evaluation measures: macro and micro-averaged F1 loss, zero-one loss and Hamming loss. Additionally, we investigated relations between classification quality, which is expressed in terms of different quality criteria, and characteristics of multi-label datasets such as average imbalance ratio or label density. The experimental study reveals that the correction approaches significantly outperforms the reference method only in terms of zero-one loss.
Tasks	Multi-Label Classification
Published	2017-10-24
URL	http://arxiv.org/abs/1710.08729v1
PDF	http://arxiv.org/pdf/1710.08729v1.pdf
PWC	https://paperswithcode.com/paper/a-correction-method-of-a-binary-classifier
Repo
Framework

Communicative Capital for Prosthetic Agents


Title	Communicative Capital for Prosthetic Agents
Authors	Patrick M. Pilarski, Richard S. Sutton, Kory W. Mathewson, Craig Sherstan, Adam S. R. Parker, Ann L. Edwards
Abstract	This work presents an overarching perspective on the role that machine intelligence can play in enhancing human abilities, especially those that have been diminished due to injury or illness. As a primary contribution, we develop the hypothesis that assistive devices, and specifically artificial arms and hands, can and should be viewed as agents in order for us to most effectively improve their collaboration with their human users. We believe that increased agency will enable more powerful interactions between human users and next generation prosthetic devices, especially when the sensorimotor space of the prosthetic technology greatly exceeds the conventional control and communication channels available to a prosthetic user. To more concretely examine an agency-based view on prosthetic devices, we propose a new schema for interpreting the capacity of a human-machine collaboration as a function of both the human’s and machine’s degrees of agency. We then introduce the idea of communicative capital as a way of thinking about the communication resources developed by a human and a machine during their ongoing interaction. Using this schema of agency and capacity, we examine the benefits and disadvantages of increasing the agency of a prosthetic limb. To do so, we present an analysis of examples from the literature where building communicative capital has enabled a progression of fruitful, task-directed interactions between prostheses and their human users. We then describe further work that is needed to concretely evaluate the hypothesis that prostheses are best thought of as agents. The agent-based viewpoint developed in this article significantly extends current thinking on how best to support the natural, functional use of increasingly complex prosthetic enhancements, and opens the door for more powerful interactions between humans and their assistive technologies.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03676v1
PDF	http://arxiv.org/pdf/1711.03676v1.pdf
PWC	https://paperswithcode.com/paper/communicative-capital-for-prosthetic-agents
Repo
Framework

Detection of Abnormal Input-Output Associations


Title	Detection of Abnormal Input-Output Associations
Authors	Charmgil Hong, Siqi Liu, Milos Hauskrecht
Abstract	We study a novel outlier detection problem that aims to identify abnormal input-output associations in data, whose instances consist of multi-dimensional input (context) and output (responses) pairs. We present our approach that works by analyzing data in the conditional (input–output) relation space, captured by a decomposable probabilistic model. Experimental results demonstrate the ability of our approach in identifying multivariate conditional outliers.
Tasks	Outlier Detection
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01035v1
PDF	http://arxiv.org/pdf/1708.01035v1.pdf
PWC	https://paperswithcode.com/paper/detection-of-abnormal-input-output
Repo
Framework

Algorithmic Performance-Accuracy Trade-off in 3D Vision Applications Using HyperMapper


Title	Algorithmic Performance-Accuracy Trade-off in 3D Vision Applications Using HyperMapper
Authors	Luigi Nardi, Bruno Bodin, Sajad Saeedi, Emanuele Vespa, Andrew J. Davison, Paul H. J. Kelly
Abstract	In this paper we investigate an emerging application, 3D scene understanding, likely to be significant in the mobile space in the near future. The goal of this exploration is to reduce execution time while meeting our quality of result objectives. In previous work we showed for the first time that it is possible to map this application to power constrained embedded systems, highlighting that decision choices made at the algorithmic design-level have the most impact. As the algorithmic design space is too large to be exhaustively evaluated, we use a previously introduced multi-objective Random Forest Active Learning prediction framework dubbed HyperMapper, to find good algorithmic designs. We show that HyperMapper generalizes on a recent cutting edge 3D scene understanding algorithm and on a modern GPU-based computer architecture. HyperMapper is able to beat an expert human hand-tuning the algorithmic parameters of the class of Computer Vision applications taken under consideration in this paper automatically. In addition, we use crowd-sourcing using a 3D scene understanding Android app to show that the Pareto front obtained on an embedded system can be used to accelerate the same application on all the 83 smart-phones and tablets crowd-sourced with speedups ranging from 2 to over 12.
Tasks	Active Learning, Scene Understanding
Published	2017-02-02
URL	http://arxiv.org/abs/1702.00505v2
PDF	http://arxiv.org/pdf/1702.00505v2.pdf
PWC	https://paperswithcode.com/paper/algorithmic-performance-accuracy-trade-off-in
Repo
Framework

Local Information with Feedback Perturbation Suffices for Dictionary Learning in Neural Circuits


Title	Local Information with Feedback Perturbation Suffices for Dictionary Learning in Neural Circuits
Authors	Tsung-Han Lin
Abstract	While the sparse coding principle can successfully model information processing in sensory neural systems, it remains unclear how learning can be accomplished under neural architectural constraints. Feasible learning rules must rely solely on synaptically local information in order to be implemented on spatially distributed neurons. We describe a neural network with spiking neurons that can address the aforementioned fundamental challenge and solve the L1-minimizing dictionary learning problem, representing the first model able to do so. Our major innovation is to introduce feedback synapses to create a pathway to turn the seemingly non-local information into local ones. The resulting network encodes the error signal needed for learning as the change of network steady states caused by feedback, and operates akin to the classical stochastic gradient descent method.
Tasks	Dictionary Learning
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07149v1
PDF	http://arxiv.org/pdf/1705.07149v1.pdf
PWC	https://paperswithcode.com/paper/local-information-with-feedback-perturbation
Repo
Framework

Parallel Complexity of Forward and Backward Propagation


Title	Parallel Complexity of Forward and Backward Propagation
Authors	Maxim Naumov
Abstract	We show that the forward and backward propagation can be formulated as a solution of lower and upper triangular systems of equations. For standard feedforward (FNNs) and recurrent neural networks (RNNs) the triangular systems are always block bi-diagonal, while for a general computation graph (directed acyclic graph) they can have a more complex triangular sparsity pattern. We discuss direct and iterative parallel algorithms that can be used for their solution and interpreted as different ways of performing model parallelism. Also, we show that for FNNs and RNNs with $k$ layers and $\tau$ time steps the backward propagation can be performed in parallel in O($\log k$) and O($\log k \log \tau$) steps, respectively. Finally, we outline the generalization of this technique using Jacobians that potentially allows us to handle arbitrary layers.
Tasks
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06577v1
PDF	http://arxiv.org/pdf/1712.06577v1.pdf
PWC	https://paperswithcode.com/paper/parallel-complexity-of-forward-and-backward
Repo
Framework

Saliency Revisited: Analysis of Mouse Movements versus Fixations


Title	Saliency Revisited: Analysis of Mouse Movements versus Fixations
Authors	Hamed R. Tavakoli, Fawad Ahmed, Ali Borji, Jorma Laaksonen
Abstract	This paper revisits visual saliency prediction by evaluating the recent advancements in this field such as crowd-sourced mouse tracking-based databases and contextual annotations. We pursue a critical and quantitative approach towards some of the new challenges including the quality of mouse tracking versus eye tracking for model training and evaluation. We extend quantitative evaluation of models in order to incorporate contextual information by proposing an evaluation methodology that allows accounting for contextual factors such as text, faces, and object attributes. The proposed contextual evaluation scheme facilitates detailed analysis of models and helps identify their pros and cons. Through several experiments, we find that (1) mouse tracking data has lower inter-participant visual congruency and higher dispersion, compared to the eye tracking data, (2) mouse tracking data does not totally agree with eye tracking in general and in terms of different contextual regions in specific, and (3) mouse tracking data leads to acceptable results in training current existing models, and (4) mouse tracking data is less reliable for model selection and evaluation. The contextual evaluation also reveals that, among the studied models, there is no single model that performs best on all the tested annotations.
Tasks	Eye Tracking, Model Selection, Saliency Prediction
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10546v1
PDF	http://arxiv.org/pdf/1705.10546v1.pdf
PWC	https://paperswithcode.com/paper/saliency-revisited-analysis-of-mouse
Repo
Framework

Neural Sequence Model Training via $α$-divergence Minimization


Title	Neural Sequence Model Training via $α$-divergence Minimization
Authors	Sotetsu Koyamada, Yuta Kikuchi, Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii
Abstract	We propose a new neural sequence model training method in which the objective function is defined by $\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning (RL)-based objective functions as special cases (i.e., ML corresponds to $\alpha \to 0$ and RL to $\alpha \to1$). We also show that the gradient of the objective function can be considered a mixture of ML- and RL-based objective gradients. The experimental results of a machine translation task show that minimizing the objective function with $\alpha > 0$ outperforms $\alpha \to 0$, which corresponds to ML-based methods.
Tasks	Machine Translation
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10031v1
PDF	http://arxiv.org/pdf/1706.10031v1.pdf
PWC	https://paperswithcode.com/paper/neural-sequence-model-training-via-divergence
Repo
Framework

Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion


Title	Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion
Authors	Peng Lei, Fuxin Li, Sinisa Todorovic
Abstract	Using deep learning, this paper addresses the problem of joint object boundary detection and boundary motion estimation in videos, which we named boundary flow estimation. Boundary flow is an important mid-level visual cue as boundaries characterize objects spatial extents, and the flow indicates objects motions and interactions. Yet, most prior work on motion estimation has focused on dense object motion or feature points that may not necessarily reside on boundaries. For boundary flow estimation, we specify a new fully convolutional Siamese network (FCSN) that jointly estimates object-level boundaries in two consecutive frames. Boundary correspondences in the two frames are predicted by the same FCSN with a new, unconventional deconvolution approach. Finally, the boundary flow estimate is improved with an edgelet-based filtering. Evaluation is conducted on three tasks: boundary detection in videos, boundary flow estimation, and optical flow estimation. On boundary detection, we achieve the state-of-the-art performance on the benchmark VSB100 dataset. On boundary flow estimation, we present the first results on the Sintel training dataset. For optical flow estimation, we run the recent approach CPMFlow but on the augmented input with our boundary-flow matches, and achieve significant performance improvement on the Sintel benchmark.
Tasks	Boundary Detection, Motion Estimation, Optical Flow Estimation
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08646v3
PDF	http://arxiv.org/pdf/1702.08646v3.pdf
PWC	https://paperswithcode.com/paper/boundary-flow-a-siamese-network-that-predicts
Repo
Framework

Barankin Vector Locally Best Unbiased Estimates


Title	Barankin Vector Locally Best Unbiased Estimates
Authors	Bruno Cernuschi-Frias
Abstract	The Barankin bound is generalized to the vector case in the mean square error sense. Necessary and sufficient conditions are obtained to achieve the lower bound. To obtain the result, a simple finite dimensional real vector valued generalization of the Riesz representation theorem for Hilbert spaces is given. The bound has the form of a linear matrix inequality where the covariances of any unbiased estimator, if these exist, are lower bounded by matrices depending only on the parametrized probability distributions.
Tasks
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10062v1
PDF	http://arxiv.org/pdf/1706.10062v1.pdf
PWC	https://paperswithcode.com/paper/barankin-vector-locally-best-unbiased
Repo
Framework

Semi-supervised Learning for Discrete Choice Models


Title	Semi-supervised Learning for Discrete Choice Models
Authors	Jie Yang, Sergey Shebalov, Diego Klabjan
Abstract	We introduce a semi-supervised discrete choice model to calibrate discrete choice models when relatively few requests have both choice sets and stated preferences but the majority only have the choice sets. Two classic semi-supervised learning algorithms, the expectation maximization algorithm and the cluster-and-label algorithm, have been adapted to our choice modeling problem setting. We also develop two new algorithms based on the cluster-and-label algorithm. The new algorithms use the Bayesian Information Criterion to evaluate a clustering setting to automatically adjust the number of clusters. Two computational studies including a hotel booking case and a large-scale airline itinerary shopping case are presented to evaluate the prediction accuracy and computational effort of the proposed algorithms. Algorithmic recommendations are rendered under various scenarios.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05137v1
PDF	http://arxiv.org/pdf/1702.05137v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-for-discrete-choice
Repo
Framework

Restricted Boltzmann Machines with Gaussian Visible Units Guided by Pairwise Constraints


Title	Restricted Boltzmann Machines with Gaussian Visible Units Guided by Pairwise Constraints
Authors	Jielei Chu, Hongjun Wang, Hua Meng, Peng Jin, Tianrui Li
Abstract	Restricted Boltzmann machines (RBMs) and their variants are usually trained by contrastive divergence (CD) learning, but the training procedure is an unsupervised learning approach, without any guidances of the background knowledge. To enhance the expression ability of traditional RBMs, in this paper, we propose pairwise constraints restricted Boltzmann machine with Gaussian visible units (pcGRBM) model, in which the learning procedure is guided by pairwise constraints and the process of encoding is conducted under these guidances. The pairwise constraints are encoded in hidden layer features of pcGRBM. Then, some pairwise hidden features of pcGRBM flock together and another part of them are separated by the guidances. In order to deal with real-valued data, the binary visible units are replaced by linear units with Gausian noise in the pcGRBM model. In the learning process of pcGRBM, the pairwise constraints are iterated transitions between visible and hidden units during CD learning procedure. Then, the proposed model is inferred by approximative gradient descent method and the corresponding learning algorithm is designed in this paper. In order to compare the availability of pcGRBM and traditional RBMs with Gaussian visible units, the features of the pcGRBM and RBMs hidden layer are used as input ‘data’ for K-means, spectral clustering (SP) and affinity propagation (AP) algorithms, respectively. A thorough experimental evaluation is performed with sixteen image datasets of Microsoft Research Asia Multimedia (MSRA-MM). The experimental results show that the clustering performance of K-means, SP and AP algorithms based on pcGRBM model are significantly better than traditional RBMs. In addition, the pcGRBM model for clustering task shows better performance than some semi-supervised clustering algorithms.
Tasks
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03647v2
PDF	http://arxiv.org/pdf/1701.03647v2.pdf
PWC	https://paperswithcode.com/paper/restricted-boltzmann-machines-with-gaussian
Repo
Framework