July 28, 2019

3098 words 15 mins read

Paper Group ANR 283

Understanding a Version of Multivariate Symmetric Uncertainty to assist in Feature Selection. SPARTan: Scalable PARAFAC2 for Large & Sparse Data. Differential Geometric Retrieval of Deep Features. Small Drone Field Experiment: Data Collection & Processing. Sample, computation vs storage tradeoffs for classification using tensor subspace models. Sha …

Understanding a Version of Multivariate Symmetric Uncertainty to assist in Feature Selection


Title	Understanding a Version of Multivariate Symmetric Uncertainty to assist in Feature Selection
Authors	Gustavo Sosa-Cabrera, Miguel García-Torres, Santiago Gómez, Christian Schaerer, Federico Divina
Abstract	In this paper, we analyze the behavior of the multivariate symmetric uncertainty (MSU) measure through the use of statistical simulation techniques under various mixes of informative and non-informative randomly generated features. Experiments show how the number of attributes, their cardinalities, and the sample size affect the MSU. We discovered a condition that preserves good quality in the MSU under different combinations of these three factors, providing a new useful criterion to help drive the process of dimension reduction.
Tasks	Dimensionality Reduction, Feature Selection
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08730v1
PDF	http://arxiv.org/pdf/1709.08730v1.pdf
PWC	https://paperswithcode.com/paper/understanding-a-version-of-multivariate
Repo
Framework

SPARTan: Scalable PARAFAC2 for Large & Sparse Data


Title	SPARTan: Scalable PARAFAC2 for Large & Sparse Data
Authors	Ioakeim Perros, Evangelos E. Papalexakis, Fei Wang, Richard Vuduc, Elizabeth Searles, Michael Thompson, Jimeng Sun
Abstract	In exploratory tensor mining, a common problem is how to analyze a set of variables across a set of subjects whose observations do not align naturally. For example, when modeling medical features across a set of patients, the number and duration of treatments may vary widely in time, meaning there is no meaningful way to align their clinical records across time points for analysis purposes. To handle such data, the state-of-the-art tensor model is the so-called PARAFAC2, which yields interpretable and robust output and can naturally handle sparse data. However, its main limitation up to now has been the lack of efficient algorithms that can handle large-scale datasets. In this work, we fill this gap by developing a scalable method to compute the PARAFAC2 decomposition of large and sparse datasets, called SPARTan. Our method exploits special structure within PARAFAC2, leading to a novel algorithmic reformulation that is both fast (in absolute time) and more memory-efficient than prior work. We evaluate SPARTan on both synthetic and real datasets, showing 22X performance gains over the best previous implementation and also handling larger problem instances for which the baseline fails. Furthermore, we are able to apply SPARTan to the mining of temporally-evolving phenotypes on data taken from real and medically complex pediatric patients. The clinical meaningfulness of the phenotypes identified in this process, as well as their temporal evolution over time for several patients, have been endorsed by clinical experts.
Tasks
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04219v1
PDF	http://arxiv.org/pdf/1703.04219v1.pdf
PWC	https://paperswithcode.com/paper/spartan-scalable-parafac2-for-large-sparse
Repo
Framework

Differential Geometric Retrieval of Deep Features


Title	Differential Geometric Retrieval of Deep Features
Authors	Y Qian, E Vazquez, B Sengupta
Abstract	Comparing images to recommend items from an image-inventory is a subject of continued interest. Added with the scalability of deep-learning architectures the once `manual’ job of hand-crafting features have been largely alleviated, and images can be compared according to features generated from a deep convolutional neural network. In this paper, we compare distance metrics (and divergences) to rank features generated from a neural network, for content-based image retrieval. Specifically, after modelling individual images using approximations of mixture models or sparse covariance estimators, we resort to their information-theoretic and Riemann geometric comparisons. We show that using approximations of mixture models enable us to compute a distance measure based on the Wasserstein metric that requires less effort than other computationally intensive optimal transport plans; finally, an affine invariant metric is used to compare the optimal transport metric to its Riemann geometric counterpart – we conclude that although expensive, retrieval metric based on Wasserstein geometry is more suitable than information theoretic comparison of images. In short, we combine GPU scalability in learning deep feature vectors with statistically efficient metrics that we foresee being utilised in a commercial setting. \|
Tasks	Content-Based Image Retrieval, Image Retrieval
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06383v2
PDF	http://arxiv.org/pdf/1702.06383v2.pdf
PWC	https://paperswithcode.com/paper/differential-geometric-retrieval-of-deep
Repo
Framework

Small Drone Field Experiment: Data Collection & Processing


Title	Small Drone Field Experiment: Data Collection & Processing
Authors	Dalton Rosario, Christoph Borel, Damon Conover, Ryan McAlinden, Anthony Ortiz, Sarah Shiver, Blair Simon
Abstract	Following an initiative formalized in April 2016 formally known as ARL West between the U.S. Army Research Laboratory (ARL) and University of Southern California’s Institute for Creative Technologies (USC ICT), a field experiment was coordinated and executed in the summer of 2016 by ARL, USC ICT, and Headwall Photonics. The purpose was to image part of the USC main campus in Los Angeles, USA, using two portable COTS (commercial off the shelf) aerial drone solutions for data acquisition, for photogrammetry (3D reconstruction from images), and fusion of hyperspectral data with the recovered set of 3D point clouds representing the target area. The research aims for determining the viability of having a machine capable of segmenting the target area into key material classes (e.g., manmade structures, live vegetation, water) for use in multiple purposes, to include providing the user with a more accurate scene understanding and enabling the unsupervised automatic sampling of meaningful material classes from the target area for adaptive semi-supervised machine learning. In the latter, a target set library may be used for automatic machine training with data of local material classes, as an example, to increase the prediction chances of machines recognizing targets. The field experiment and associated data post processing approach to correct for reflectance, geo-rectify, recover the area’s dense point clouds from images, register spectral with elevation properties of scene surfaces from the independently collected datasets, and generate the desired scene segmented maps are discussed. Lessons learned from the experience are also highlighted throughout the paper.
Tasks	3D Reconstruction, Scene Understanding
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10693v1
PDF	http://arxiv.org/pdf/1711.10693v1.pdf
PWC	https://paperswithcode.com/paper/small-drone-field-experiment-data-collection
Repo
Framework

Sample, computation vs storage tradeoffs for classification using tensor subspace models


Title	Sample, computation vs storage tradeoffs for classification using tensor subspace models
Authors	Mohammadhossein Chaghazardi, Shuchin Aeron
Abstract	In this paper, we exhibit the tradeoffs between the (training) sample, computation and storage complexity for the problem of supervised classification using signal subspace estimation. Our main tool is the use of tensor subspaces, i.e. subspaces with a Kronecker structure, for embedding the data into lower dimensions. Among the subspaces with a Kronecker structure, we show that using subspaces with a hierarchical structure for representing data leads to improved tradeoffs. One of the main reasons for the improvement is that embedding data into these hierarchical Kronecker structured subspaces prevents overfitting at higher latent dimensions.
Tasks
Published	2017-06-18
URL	http://arxiv.org/abs/1706.05599v3
PDF	http://arxiv.org/pdf/1706.05599v3.pdf
PWC	https://paperswithcode.com/paper/sample-computation-vs-storage-tradeoffs-for
Repo
Framework

Shading Annotations in the Wild


Title	Shading Annotations in the Wild
Authors	Balazs Kovacs, Sean Bell, Noah Snavely, Kavita Bala
Abstract	Understanding shading effects in images is critical for a variety of vision and graphics problems, including intrinsic image decomposition, shadow removal, image relighting, and inverse rendering. As is the case with other vision tasks, machine learning is a promising approach to understanding shading - but there is little ground truth shading data available for real-world images. We introduce Shading Annotations in the Wild (SAW), a new large-scale, public dataset of shading annotations in indoor scenes, comprised of multiple forms of shading judgments obtained via crowdsourcing, along with shading annotations automatically generated from RGB-D imagery. We use this data to train a convolutional neural network to predict per-pixel shading information in an image. We demonstrate the value of our data and network in an application to intrinsic images, where we can reduce decomposition artifacts produced by existing algorithms. Our database is available at http://opensurfaces.cs.cornell.edu/saw/.
Tasks	Intrinsic Image Decomposition
Published	2017-05-02
URL	http://arxiv.org/abs/1705.01156v1
PDF	http://arxiv.org/pdf/1705.01156v1.pdf
PWC	https://paperswithcode.com/paper/shading-annotations-in-the-wild
Repo
Framework

A Generative Model for Score Normalization in Speaker Recognition


Title	A Generative Model for Score Normalization in Speaker Recognition
Authors	Albert Swart, Niko Brummer
Abstract	We propose a theoretical framework for thinking about score normalization, which confirms that normalization is not needed under (admittedly fragile) ideal conditions. If, however, these conditions are not met, e.g. under data-set shift between training and runtime, our theory reveals dependencies between scores that could be exploited by strategies such as score normalization. Indeed, it has been demonstrated over and over experimentally, that various ad-hoc score normalization recipes do work. We present a first attempt at using probability theory to design a generative score-space normalization model which gives similar improvements to ZT-norm on the text-dependent RSR 2015 database.
Tasks	Speaker Recognition
Published	2017-09-28
URL	http://arxiv.org/abs/1709.09868v1
PDF	http://arxiv.org/pdf/1709.09868v1.pdf
PWC	https://paperswithcode.com/paper/a-generative-model-for-score-normalization-in
Repo
Framework

Spectral estimation of the percolation transition in clustered networks


Title	Spectral estimation of the percolation transition in clustered networks
Authors	Pan Zhang
Abstract	There have been several spectral bounds for the percolation transition in networks, using spectrum of matrices associated with the network such as the adjacency matrix and the non-backtracking matrix. However they are far from being tight when the network is sparse and displays clustering or transitivity, which is represented by existence of short loops e.g. triangles. In this work, for the bond percolation, we first propose a message passing algorithm for calculating size of percolating clusters considering effects of triangles, then relate the percolation transition to the leading eigenvalue of a matrix that we name the triangle-non-backtracking matrix, by analyzing stability of the message passing equations. We establish that our method gives a tighter lower-bound to the bond percolation transition than previous spectral bounds, and it becomes exact for an infinite network with no loops longer than 3. We evaluate numerically our methods on synthetic and real-world networks, and discuss further generalizations of our approach to include higher-order sub-structures.
Tasks
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01592v1
PDF	http://arxiv.org/pdf/1710.01592v1.pdf
PWC	https://paperswithcode.com/paper/spectral-estimation-of-the-percolation
Repo
Framework

Improving speaker turn embedding by crossmodal transfer learning from face embedding


Title	Improving speaker turn embedding by crossmodal transfer learning from face embedding
Authors	Nam Le, Jean-Marc Odobez
Abstract	Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding learning, which has been proven very successful for face verification and clustering tasks. Assuming that face and voices from the same identities share some latent properties (like age, gender, ethnicity), we propose three transfer learning approaches to leverage the knowledge from the face domain (learned from thousands of images and identities) for tasks in the speaker domain. These approaches, namely target embedding transfer, relative distance transfer, and clustering structure transfer, utilize the structure of the source face embedding space at different granularities to regularize the target speaker turn embedding space as optimizing terms. Our methods are evaluated on two public broadcast corpora and yield promising advances over competitive baselines in verification and audio clustering tasks, especially when dealing with short speaker utterances. The analysis of the results also gives insight into characteristics of the embedding spaces and shows their potential applications.
Tasks	Face Verification, Transfer Learning
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02749v1
PDF	http://arxiv.org/pdf/1707.02749v1.pdf
PWC	https://paperswithcode.com/paper/improving-speaker-turn-embedding-by
Repo
Framework

Knowledge Fusion via Embeddings from Text, Knowledge Graphs, and Images


Title	Knowledge Fusion via Embeddings from Text, Knowledge Graphs, and Images
Authors	Steffen Thoma, Achim Rettinger, Fabian Both
Abstract	We present a baseline approach for cross-modal knowledge fusion. Different basic fusion methods are evaluated on existing embedding approaches to show the potential of joining knowledge about certain concepts across modalities in a fused concept representation.
Tasks	Knowledge Graphs
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06084v1
PDF	http://arxiv.org/pdf/1704.06084v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-fusion-via-embeddings-from-text
Repo
Framework

One-pass Person Re-identification by Sketch Online Discriminant Analysis


Title	One-pass Person Re-identification by Sketch Online Discriminant Analysis
Authors	Wei-Hong Li, Zhuowei Zhong, Wei-Shi Zheng
Abstract	Person re-identification (re-id) is to match people across disjoint camera views in a multi-camera system, and re-id has been an important technology applied in smart city in recent years. However, the majority of existing person re-id methods are not designed for processing sequential data in an online way. This ignores the real-world scenario that person images detected from multi-cameras system are coming sequentially. While there is a few work on discussing online re-id, most of them require considerable storage of all passed data samples that have been ever observed, and this could be unrealistic for processing data from a large camera network. In this work, we present an onepass person re-id model that adapts the re-id model based on each newly observed data and no passed data are directly used for each update. More specifically, we develop an Sketch online Discriminant Analysis (SoDA) by embedding sketch processing into Fisher discriminant analysis (FDA). SoDA can efficiently keep the main data variations of all passed samples in a low rank matrix when processing sequential data samples, and estimate the approximate within-class variance (i.e. within-class covariance matrix) from the sketch data information. We provide theoretical analysis on the effect of the estimated approximate within-class covariance matrix. In particular, we derive upper and lower bounds on the Fisher discriminant score (i.e. the quotient between between-class variation and within-class variation after feature transformation) in order to investigate how the optimal feature transformation learned by SoDA sequentially approximates the offline FDA that is learned on all observed data. Extensive experimental results have shown the effectiveness of our SoDA and empirically support our theoretical analysis.
Tasks	Person Re-Identification
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03368v1
PDF	http://arxiv.org/pdf/1711.03368v1.pdf
PWC	https://paperswithcode.com/paper/one-pass-person-re-identification-by-sketch
Repo
Framework

Generalized notions of sparsity and restricted isometry property. Part I: A unified framework


Title	Generalized notions of sparsity and restricted isometry property. Part I: A unified framework
Authors	Marius Junge, Kiryung Lee
Abstract	The restricted isometry property (RIP) is an integral tool in the analysis of various inverse problems with sparsity models. Motivated by the applications of compressed sensing and dimensionality reduction of low-rank tensors, we propose generalized notions of sparsity and provide a unified framework for the corresponding RIP, in particular when combined with isotropic group actions. Our results extend an approach by Rudelson and Vershynin to a much broader context including commutative and noncommutative function spaces. Moreover, our Banach space notion of sparsity applies to affine group actions. The generalized approach in particular applies to high order tensor products.
Tasks	Dimensionality Reduction
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09410v2
PDF	http://arxiv.org/pdf/1706.09410v2.pdf
PWC	https://paperswithcode.com/paper/generalized-notions-of-sparsity-and-1
Repo
Framework

On the links between argumentation-based reasoning and nonmonotonic reasoning


Title	On the links between argumentation-based reasoning and nonmonotonic reasoning
Authors	Zimi Li, Nir Oren, Simon Parsons
Abstract	In this paper we investigate the links between instantiated argumentation systems and the axioms for non-monotonic reasoning described in [9] with the aim of characterising the nature of argument based reasoning. In doing so, we consider two possible interpretations of the consequence relation, and describe which axioms are met by ASPIC+ under each of these interpretations. We then consider the links between these axioms and the rationality postulates. Our results indicate that argument based reasoning as characterised by ASPIC+ is - according to the axioms of [9] - non-cumulative and non-monotonic, and therefore weaker than the weakest non-monotonic reasoning systems they considered possible. This weakness underpins ASPIC+'s success in modelling other reasoning systems, and we conclude by considering the relationship between ASPIC+ and other weak logical systems.
Tasks
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03714v1
PDF	http://arxiv.org/pdf/1701.03714v1.pdf
PWC	https://paperswithcode.com/paper/on-the-links-between-argumentation-based
Repo
Framework

Gradient Descent for Spiking Neural Networks


Title	Gradient Descent for Spiking Neural Networks
Authors	Dongsung Huh, Terrence J. Sejnowski
Abstract	Much of studies on neural computation are based on network models of static neurons that produce analog output, despite the fact that information processing in the brain is predominantly carried out by dynamic neurons that produce discrete pulses called spikes. Research in spike-based computation has been impeded by the lack of efficient supervised learning algorithm for spiking networks. Here, we present a gradient descent method for optimizing spiking network models by introducing a differentiable formulation of spiking networks and deriving the exact gradient calculation. For demonstration, we trained recurrent spiking networks on two dynamic tasks: one that requires optimizing fast (~millisecond) spike-based interactions for efficient encoding of information, and a delayed memory XOR task over extended duration (~second). The results show that our method indeed optimizes the spiking network dynamics on the time scale of individual spikes as well as behavioral time scales. In conclusion, our result offers a general purpose supervised learning algorithm for spiking neural networks, thus advancing further investigations on spike-based computation.
Tasks
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04698v2
PDF	http://arxiv.org/pdf/1706.04698v2.pdf
PWC	https://paperswithcode.com/paper/gradient-descent-for-spiking-neural-networks
Repo
Framework

Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human–like learning


Title	Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human–like learning
Authors	Pierre-Yves Oudeyer
Abstract	Autonomous lifelong development and learning is a fundamental capability of humans, differentiating them from current deep learning systems. However, other branches of artificial intelligence have designed crucial ingredients towards autonomous learning: curiosity and intrinsic motivation, social learning and natural interaction with peers, and embodiment. These mechanisms guide exploration and autonomous choice of goals, and integrating them with deep learning opens stimulating perspectives. Deep learning (DL) approaches made great advances in artificial intelligence, but are still far away from human learning. As argued convincingly by Lake et al., differences include human capabilities to learn causal models of the world from very little data, leveraging compositional representations and priors like intuitive physics and psychology. However, there are other fundamental differences between current DL systems and human learning, as well as technical ingredients to fill this gap, that are either superficially, or not adequately, discussed by Lake et al. These fundamental mechanisms relate to autonomous development and learning. They are bound to play a central role in artificial intelligence in the future. Current DL systems require engineers to manually specify a task-specific objective function for every new task, and learn through off-line processing of large training databases. On the contrary, humans learn autonomously open-ended repertoires of skills, deciding for themselves which goals to pursue or value, and which skills to explore, driven by intrinsic motivation/curiosity and social learning through natural interaction with peers. Such learning processes are incremental, online, and progressive. Human child development involves a progressive increase of complexity in a curriculum of learning where skills are explored, acquired, and built on each other, through particular ordering and timing. Finally, human learning happens in the physical world, and through bodily and physical experimentation, under severe constraints on energy, time, and computational resources. In the two last decades, the field of Developmental and Cognitive Robotics (Cangelosi and Schlesinger, 2015, Asada et al., 2009), in strong interaction with developmental psychology and neuroscience, has achieved significant advances in computational
Tasks
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01626v1
PDF	http://arxiv.org/pdf/1712.01626v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-development-and-learning-in
Repo
Framework