May 7, 2019

2860 words 14 mins read

Paper Group ANR 12

Stochastic Backpropagation through Mixture Density Distributions. UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones. Recurrent Memory Addressing for describing videos. Multidimensional Binary Search for Contextual Decision-Making. A Recursive Born Approach to Nonlinear Inverse Scattering. Machine Lea …

Stochastic Backpropagation through Mixture Density Distributions


Title	Stochastic Backpropagation through Mixture Density Distributions
Authors	Alex Graves
Abstract	The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an unbiased and low-variance way of estimating gradients with respect to distribution parameters from gradients evaluated at distribution samples. The “reparameterization trick” provides a class of transforms yielding such estimators for many continuous distributions, including the Gaussian and other members of the location-scale family. However the trick does not readily extend to mixture density models, due to the difficulty of reparameterizing the discrete distribution over mixture weights. This report describes an alternative transform, applicable to any continuous multivariate distribution with a differentiable density function from which samples can be drawn, and uses it to derive an unbiased estimator for mixture density weight derivatives. Combined with the reparameterization trick applied to the individual mixture components, this estimator makes it straightforward to train variational autoencoders with mixture-distributed latent variables, or to perform stochastic variational inference with a mixture density variational posterior.
Tasks
Published	2016-07-19
URL	http://arxiv.org/abs/1607.05690v1
PDF	http://arxiv.org/pdf/1607.05690v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-backpropagation-through-mixture
Repo
Framework

UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones


Title	UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones
Authors	Daniela Micucci, Marco Mobilio, Paolo Napoletano
Abstract	Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being increasingly used to monitor human activities. Data acquired by the hosted sensors are usually processed by machine-learning-based algorithms to classify human activities. The success of those algorithms mostly depends on the availability of training (labeled) data that, if made publicly available, would allow researchers to make objective comparisons between techniques. Nowadays, publicly available data sets are few, often contain samples from subjects with too similar characteristics, and very often lack of specific information so that is not possible to select subsets of samples according to specific criteria. In this article, we present a new dataset of acceleration samples acquired with an Android smartphone designed for human activity recognition and fall detection. The dataset includes 11,771 samples of both human activities and falls performed by 30 subjects of ages ranging from 18 to 60 years. Samples are divided in 17 fine grained classes grouped in two coarse grained classes: one containing samples of 9 types of activities of daily living (ADL) and the other containing samples of 8 types of falls. The dataset has been stored to include all the information useful to select samples according to different criteria, such as the type of ADL, the age, the gender, and so on. Finally, the dataset has been benchmarked with four different classifiers and with two different feature vectors. We evaluated four different classification tasks: fall vs no fall, 9 activities, 8 falls, 17 activities and falls. For each classification task we performed a subject-dependent and independent evaluation. The major findings of the evaluation are the following: i) it is more difficult to distinguish between types of falls than types of activities; ii) subject-dependent evaluation outperforms the subject-independent one
Tasks	Activity Recognition, Human Activity Recognition
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07688v5
PDF	http://arxiv.org/pdf/1611.07688v5.pdf
PWC	https://paperswithcode.com/paper/unimib-shar-a-new-dataset-for-human-activity
Repo
Framework

Recurrent Memory Addressing for describing videos


Title	Recurrent Memory Addressing for describing videos
Authors	Arnav Kumar Jain, Abhinav Agarwalla, Kumar Krishna Agrawal, Pabitra Mitra
Abstract	In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models. The proposed model naturally decomposes the problem of video captioning into vision and language segments, dealing with them as key-value pairs. More specifically, we learn a semantic embedding (v) corresponding to each frame (k) in the video, thereby creating (k, v) memory slots. We propose to find the next step attention weights conditioned on the previous attention distributions for the key-value memory slots in the memory addressing schema. Exploiting this flexibility of the framework, we additionally capture spatial dependencies while mapping from the visual to semantic embedding. Experiments done on the Youtube2Text dataset demonstrate usefulness of recurrent key-addressing, while achieving competitive scores on BLEU@4, METEOR metrics against state-of-the-art models.
Tasks	Video Captioning
Published	2016-11-20
URL	http://arxiv.org/abs/1611.06492v2
PDF	http://arxiv.org/pdf/1611.06492v2.pdf
PWC	https://paperswithcode.com/paper/recurrent-memory-addressing-for-describing
Repo
Framework

Multidimensional Binary Search for Contextual Decision-Making


Title	Multidimensional Binary Search for Contextual Decision-Making
Authors	Ilan Lobel, Renato Paes Leme, Adrian Vladu
Abstract	We consider a multidimensional search problem that is motivated by questions in contextual decision-making, such as dynamic pricing and personalized medicine. Nature selects a state from a $d$-dimensional unit ball and then generates a sequence of $d$-dimensional directions. We are given access to the directions, but not access to the state. After receiving a direction, we have to guess the value of the dot product between the state and the direction. Our goal is to minimize the number of times when our guess is more than $\epsilon$ away from the true answer. We construct a polynomial time algorithm that we call Projected Volume achieving regret $O(d\log(d/\epsilon))$, which is optimal up to a $\log d$ factor. The algorithm combines a volume cutting strategy with a new geometric technique that we call cylindrification.
Tasks	Decision Making
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00829v2
PDF	http://arxiv.org/pdf/1611.00829v2.pdf
PWC	https://paperswithcode.com/paper/multidimensional-binary-search-for-contextual
Repo
Framework

A Recursive Born Approach to Nonlinear Inverse Scattering


Title	A Recursive Born Approach to Nonlinear Inverse Scattering
Authors	Ulugbek S. Kamilov, Dehong Liu, Hassan Mansour, Petros T. Boufounos
Abstract	The Iterative Born Approximation (IBA) is a well-known method for describing waves scattered by semi-transparent objects. In this paper, we present a novel nonlinear inverse scattering method that combines IBA with an edge-preserving total variation (TV) regularizer. The proposed method is obtained by relating iterations of IBA to layers of a feedforward neural network and developing a corresponding error backpropagation algorithm for efficiently estimating the permittivity of the object. Simulations illustrate that, by accounting for multiple scattering, the method successfully recovers the permittivity distribution where the traditional linear inverse scattering fails.
Tasks
Published	2016-03-11
URL	http://arxiv.org/abs/1603.03768v1
PDF	http://arxiv.org/pdf/1603.03768v1.pdf
PWC	https://paperswithcode.com/paper/a-recursive-born-approach-to-nonlinear
Repo
Framework

Machine Learning for Antimicrobial Resistance


Title	Machine Learning for Antimicrobial Resistance
Authors	John W. Santerre, James J. Davis, Fangfang Xia, Rick Stevens
Abstract	Biological datasets amenable to applied machine learning are more available today than ever before, yet they lack adequate representation in the Data-for-Good community. Here we present a work in progress case study performing analysis on antimicrobial resistance (AMR) using standard ensemble machine learning techniques and note the successes and pitfalls such work entails. Broadly, applied machine learning (AML) techniques are well suited to AMR, with classification accuracies ranging from mid-90% to low- 80% depending on sample size. Additionally, these techniques prove successful at identifying gene regions known to be associated with the AMR phenotype. We believe that the extensive amount of biological data available, the plethora of problems presented, and the global impact of such work merits the consideration of the Data- for-Good community.
Tasks
Published	2016-07-05
URL	http://arxiv.org/abs/1607.01224v1
PDF	http://arxiv.org/pdf/1607.01224v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-antimicrobial-resistance
Repo
Framework

Inverses, Conditionals and Compositional Operators in Separative Valuation Algebra


Title	Inverses, Conditionals and Compositional Operators in Separative Valuation Algebra
Authors	Juerg Kohlas
Abstract	Compositional models were introduce by Jirousek and Shenoy in the general framework of valuation-based systems. They based their theory on an axiomatic system of valuations involving not only the operations of combination and marginalisation, but also of removal. They claimed that this systems covers besides the classical case of discrete probability distributions, also the cases of Gaussian densities and belief functions, and many other systems. Whereas their results on the compositional operator are correct, the axiomatic basis is not sufficient to cover the examples claimed above. We propose here a different axiomatic system of valuation algebras, which permits a rigorous mathematical theory of compositional operators in valuation-based systems and covers all the examples mentioned above. It extends the classical theory of inverses in semigroup theory and places thereby the present theory into its proper mathematical frame. Also this theory sheds light on the different structures of valuation-based systems, like regular algebras (represented by probability potentials), canncellative algebras (Gaussian potentials) and general separative algebras (density functions).
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.02587v1
PDF	http://arxiv.org/pdf/1612.02587v1.pdf
PWC	https://paperswithcode.com/paper/inverses-conditionals-and-compositional
Repo
Framework

Approximation and Parameterized Complexity of Minimax Approval Voting


Title	Approximation and Parameterized Complexity of Minimax Approval Voting
Authors	Marek Cygan, Łukasz Kowalik, Arkadiusz Socała, Krzysztof Sornat
Abstract	We present three results on the complexity of Minimax Approval Voting. First, we study Minimax Approval Voting parameterized by the Hamming distance $d$ from the solution to the votes. We show Minimax Approval Voting admits no algorithm running in time $\mathcal{O}^\star(2^{o(d\log d)})$, unless the Exponential Time Hypothesis (ETH) fails. This means that the $\mathcal{O}^\star(d^{2d})$ algorithm of Misra et al. [AAMAS 2015] is essentially optimal. Motivated by this, we then show a parameterized approximation scheme, running in time $\mathcal{O}^\star(\left({3}/{\epsilon}\right)^{2d})$, which is essentially tight assuming ETH. Finally, we get a new polynomial-time randomized approximation scheme for Minimax Approval Voting, which runs in time $n^{\mathcal{O}(1/\epsilon^2 \cdot \log(1/\epsilon))} \cdot \mathrm{poly}(m)$, almost matching the running time of the fastest known PTAS for Closest String due to Ma and Sun [SIAM J. Comp. 2009].
Tasks
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07906v1
PDF	http://arxiv.org/pdf/1607.07906v1.pdf
PWC	https://paperswithcode.com/paper/approximation-and-parameterized-complexity-of
Repo
Framework

Differential Angular Imaging for Material Recognition


Title	Differential Angular Imaging for Material Recognition
Authors	Jia Xue, Hang Zhang, Kristin Dana, Ko Nishino
Abstract	Material recognition for real-world outdoor surfaces has become increasingly important for computer vision to support its operation “in the wild.” Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined images of materials captured in the scene. We propose to take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture. We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement. We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, geared towards real use for autonomous agents. The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions. We develop a novel approach for material recognition called a Differential Angular Imaging Network (DAIN) to fully leverage this large dataset. With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance. Our results show that DAIN achieves recognition performance that surpasses single view or coarsely quantized multiview images. These results demonstrate the effectiveness of differential angular imaging as a means for flexible, in-place material recognition.
Tasks	Material Recognition
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02372v2
PDF	http://arxiv.org/pdf/1612.02372v2.pdf
PWC	https://paperswithcode.com/paper/differential-angular-imaging-for-material
Repo
Framework

Bibliographic Analysis on Research Publications using Authors, Categorical Labels and the Citation Network


Title	Bibliographic Analysis on Research Publications using Authors, Categorical Labels and the Citation Network
Authors	Kar Wai Lim, Wray Buntine
Abstract	Bibliographic analysis considers the author’s research areas, the citation network and the paper content among other things. In this paper, we combine these three in a topic model that produces a bibliographic model of authors, topics and documents, using a nonparametric extension of a combination of the Poisson mixed-topic link model and the author-topic model. This gives rise to the Citation Network Topic Model (CNTM). We propose a novel and efficient inference algorithm for the CNTM to explore subsets of research publications from CiteSeerX. The publication datasets are organised into three corpora, totalling to about 168k publications with about 62k authors. The queried datasets are made available online. In three publicly available corpora in addition to the queried datasets, our proposed model demonstrates an improved performance in both model fitting and document clustering, compared to several baselines. Moreover, our model allows extraction of additional useful knowledge from the corpora, such as the visualisation of the author-topics network. Additionally, we propose a simple method to incorporate supervision into topic modelling to achieve further improvement on the clustering task.
Tasks
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06532v1
PDF	http://arxiv.org/pdf/1609.06532v1.pdf
PWC	https://paperswithcode.com/paper/bibliographic-analysis-on-research
Repo
Framework

A Survey of Pansharpening Methods with A New Band-Decoupled Variational Model


Title	A Survey of Pansharpening Methods with A New Band-Decoupled Variational Model
Authors	Joan Duran, Antoni Buades, Bartomeu Coll, Catalina Sbert, Gwendoline Blanchet
Abstract	Most satellites decouple the acquisition of a panchromatic image at high spatial resolution from the acquisition of a multispectral image at lower spatial resolution. Pansharpening is a fusion technique used to increase the spatial resolution of the multispectral data while simultaneously preserving its spectral information. In this paper, we consider pansharpening as an optimization problem minimizing a cost function with a nonlocal regularization term. The energy functional which is to be minimized decouples for each band, thus permitting the application to misregistered spectral components. This requirement is achieved by dropping the, commonly used, assumption that relates the spectral and panchromatic modalities by a linear transformation. Instead, a new constraint that preserves the radiometric ratio between the panchromatic and each spectral component is introduced. An exhaustive performance comparison of the proposed fusion method with several classical and state-of-the-art pansharpening techniques illustrates its superiority in preserving spatial details, reducing color distortions, and avoiding the creation of aliasing artifacts.
Tasks
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05703v1
PDF	http://arxiv.org/pdf/1606.05703v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-pansharpening-methods-with-a-new
Repo
Framework

Multiple objects tracking in surveillance video using color and Hu moments


Title	Multiple objects tracking in surveillance video using color and Hu moments
Authors	Chandrajit M, Girisha R, Vasudev T
Abstract	Multiple objects tracking finds its applications in many high level vision analysis like object behaviour interpretation and gait recognition. In this paper, a feature based method to track the multiple moving objects in surveillance video sequence is proposed. Object tracking is done by extracting the color and Hu moments features from the motion segmented object blob and establishing the association of objects in the successive frames of the video sequence based on Chi-Square dissimilarity measure and nearest neighbor classifier. The benchmark IEEE PETS and IEEE Change Detection datasets has been used to show the robustness of the proposed method. The proposed method is assessed quantitatively using the precision and recall accuracy metrics. Further, comparative evaluation with related works has been carried out to exhibit the efficacy of the proposed method.
Tasks	Accuracy Metrics, Gait Recognition, Object Tracking
Published	2016-08-22
URL	http://arxiv.org/abs/1608.06148v2
PDF	http://arxiv.org/pdf/1608.06148v2.pdf
PWC	https://paperswithcode.com/paper/multiple-objects-tracking-in-surveillance
Repo
Framework

Learning values across many orders of magnitude


Title	Learning values across many orders of magnitude
Authors	Hado van Hasselt, Arthur Guez, Matteo Hessel, Volodymyr Mnih, David Silver
Abstract	Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior. Our main motivation is prior work on learning to play Atari games, where the rewards were all clipped to a predetermined range. This clipping facilitates learning across many different games with a single learning algorithm, but a clipped reward function can result in qualitatively different behavior. Using the adaptive normalization we can remove this domain-specific heuristic without diminishing overall performance.
Tasks	Atari Games
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07714v2
PDF	http://arxiv.org/pdf/1602.07714v2.pdf
PWC	https://paperswithcode.com/paper/learning-values-across-many-orders-of
Repo
Framework

Group Equivariant Convolutional Networks


Title	Group Equivariant Convolutional Networks
Authors	Taco S. Cohen, Max Welling
Abstract	We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and rotations. G-CNNs achieve state of the art results on CIFAR10 and rotated MNIST.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07576v3
PDF	http://arxiv.org/pdf/1602.07576v3.pdf
PWC	https://paperswithcode.com/paper/group-equivariant-convolutional-networks
Repo
Framework

Degrees of Freedom in Deep Neural Networks


Title	Degrees of Freedom in Deep Neural Networks
Authors	Tianxiang Gao, Vladimir Jojic
Abstract	In this paper, we explore degrees of freedom in deep sigmoidal neural networks. We show that the degrees of freedom in these models is related to the expected optimism, which is the expected difference between test error and training error. We provide an efficient Monte-Carlo method to estimate the degrees of freedom for multi-class classification methods. We show degrees of freedom are lower than the parameter count in a simple XOR network. We extend these results to neural nets trained on synthetic and real data, and investigate impact of network’s architecture and different regularization choices. The degrees of freedom in deep networks are dramatically smaller than the number of parameters, in some real datasets several orders of magnitude. Further, we observe that for fixed number of parameters, deeper networks have less degrees of freedom exhibiting a regularization-by-depth.
Tasks
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09260v2
PDF	http://arxiv.org/pdf/1603.09260v2.pdf
PWC	https://paperswithcode.com/paper/degrees-of-freedom-in-deep-neural-networks
Repo
Framework