May 5, 2019

2969 words 14 mins read

Paper Group ANR 453

Studying Very Low Resolution Recognition Using Deep Networks. Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks. Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks. Deep Pyramidal Residual Networks with Separated Stochastic Depth. Multitask P …

Studying Very Low Resolution Recognition Using Deep Networks


Title	Studying Very Low Resolution Recognition Using Deep Networks
Authors	Zhangyang Wang, Shiyu Chang, Yingzhen Yang, Ding Liu, Thomas S. Huang
Abstract	Visual recognition research often assumes a sufficient resolution of the region of interest (ROI). That is usually violated in practice, inspiring us to explore the Very Low Resolution Recognition (VLRR) problem. Typically, the ROI in a VLRR problem can be smaller than $16 \times 16$ pixels, and is challenging to be recognized even by human experts. We attempt to solve the VLRR problem using deep learning methods. Taking advantage of techniques primarily in super resolution, domain adaptation and robust regression, we formulate a dedicated deep learning method and demonstrate how these techniques are incorporated step by step. Any extra complexity, when introduced, is fully justified by both analysis and simulation results. The resulting \textit{Robust Partially Coupled Networks} achieves feature enhancement and recognition simultaneously. It allows for both the flexibility to combat the LR-HR domain mismatch, and the robustness to outliers. Finally, the effectiveness of the proposed models is evaluated on three different VLRR tasks, including face identification, digit recognition and font recognition, all of which obtain very impressive performances.
Tasks	Domain Adaptation, Face Identification, Super-Resolution
Published	2016-01-16
URL	http://arxiv.org/abs/1601.04153v2
PDF	http://arxiv.org/pdf/1601.04153v2.pdf
PWC	https://paperswithcode.com/paper/studying-very-low-resolution-recognition
Repo
Framework

Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks


Title	Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
Authors	Pichao Wang, Zhaoyang Li, Yonghong Hou, Wanqing Li
Abstract	Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In this paper, we propose a compact, effective yet simple method to encode spatio-temporal information carried in $3D$ skeleton sequences into multiple $2D$ images, referred to as Joint Trajectory Maps (JTM), and ConvNets are adopted to exploit the discriminative features for real-time human action recognition. The proposed method has been evaluated on three public benchmarks, i.e., MSRC-12 Kinect gesture dataset (MSRC-12), G3D dataset and UTD multimodal human action dataset (UTD-MHAD) and achieved the state-of-the-art results.
Tasks	Temporal Action Localization
Published	2016-11-08
URL	http://arxiv.org/abs/1611.02447v2
PDF	http://arxiv.org/pdf/1611.02447v2.pdf
PWC	https://paperswithcode.com/paper/action-recognition-based-on-joint-trajectory-1
Repo
Framework

Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks


Title	Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks
Authors	Marcos Vinícius Treviso, Christopher Shulby, Sandra Maria Aluísio
Abstract	Automated discourse analysis tools based on Natural Language Processing (NLP) aiming at the diagnosis of language-impairing dementias generally extract several textual metrics of narrative transcripts. However, the absence of sentence boundary segmentation in the transcripts prevents the direct application of NLP methods which rely on these marks to function properly, such as taggers and parsers. We present the first steps taken towards automatic neuropsychological evaluation based on narrative discourse analysis, presenting a new automatic sentence segmentation method for impaired speech. Our model uses recurrent convolutional neural networks with prosodic, Part of Speech (PoS) features, and word embeddings. It was evaluated intrinsically on impaired, spontaneous speech, as well as, normal, prepared speech, and presents better results for healthy elderly (CTL) (F1 = 0.74) and Mild Cognitive Impairment (MCI) patients (F1 = 0.70) than the Conditional Random Fields method (F1 = 0.55 and 0.53, respectively) used in the same context of our study. The results suggest that our model is robust for impaired speech and can be used in automated discourse analysis tools to differentiate narratives produced by MCI and CTL.
Tasks	Word Embeddings
Published	2016-10-02
URL	http://arxiv.org/abs/1610.00211v2
PDF	http://arxiv.org/pdf/1610.00211v2.pdf
PWC	https://paperswithcode.com/paper/sentence-segmentation-in-narrative
Repo
Framework

Deep Pyramidal Residual Networks with Separated Stochastic Depth


Title	Deep Pyramidal Residual Networks with Separated Stochastic Depth
Authors	Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise
Abstract	On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy. In particular, ResNet and its improvements have broken the lowest error rate records. In this paper, we propose a method to successfully combine two ResNet improvements, ResDrop and PyramidNet. We confirmed that the proposed network outperformed the conventional methods; on CIFAR-100, the proposed network achieved an error rate of 16.18% in contrast to PiramidNet achieving that of 18.29% and ResNeXt 17.31%.
Tasks	Object Recognition
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01230v1
PDF	http://arxiv.org/pdf/1612.01230v1.pdf
PWC	https://paperswithcode.com/paper/deep-pyramidal-residual-networks-with
Repo
Framework

Multitask Protein Function Prediction Through Task Dissimilarity


Title	Multitask Protein Function Prediction Through Task Dissimilarity
Authors	Marco Frasca, Nicolò Cesa Bianchi
Abstract	Automated protein function prediction is a challenging problem with distinctive features, such as the hierarchical organization of protein functions and the scarcity of annotated proteins for most biological functions. We propose a multitask learning algorithm addressing both issues. Unlike standard multitask algorithms, which use task (protein functions) similarity information as a bias to speed up learning, we show that dissimilarity information enforces separation of rare class labels from frequent class labels, and for this reason is better suited for solving unbalanced protein function prediction problems. We support our claim by showing that a multitask extension of the label propagation algorithm empirically works best when the task relatedness information is represented using a dissimilarity matrix as opposed to a similarity matrix. Moreover, the experimental comparison carried out on three model organism shows that our method has a more stable performance in both “protein-centric” and “function-centric” evaluation settings.
Tasks	Protein Function Prediction
Published	2016-11-03
URL	http://arxiv.org/abs/1611.00962v1
PDF	http://arxiv.org/pdf/1611.00962v1.pdf
PWC	https://paperswithcode.com/paper/multitask-protein-function-prediction-through
Repo
Framework

Towards Instance Optimal Bounds for Best Arm Identification


Title	Towards Instance Optimal Bounds for Best Arm Identification
Authors	Lijie Chen, Jian Li, Mingda Qiao
Abstract	In the classical best arm identification (Best-$1$-Arm) problem, we are given $n$ stochastic bandit arms, each associated with a reward distribution with an unknown mean. We would like to identify the arm with the largest mean with probability at least $1-\delta$, using as few samples as possible. Understanding the sample complexity of Best-$1$-Arm has attracted significant attention since the last decade. However, the exact sample complexity of the problem is still unknown. Recently, Chen and Li made the gap-entropy conjecture concerning the instance sample complexity of Best-$1$-Arm. Given an instance $I$, let $\mu_{[i]}$ be the $i$th largest mean and $\Delta_{[i]}=\mu_{[1]}-\mu_{[i]}$ be the corresponding gap. $H(I)=\sum_{i=2}^n\Delta_{[i]}^{-2}$ is the complexity of the instance. The gap-entropy conjecture states that $\Omega\left(H(I)\cdot\left(\ln\delta^{-1}+\mathsf{Ent}(I)\right)\right)$ is an instance lower bound, where $\mathsf{Ent}(I)$ is an entropy-like term determined by the gaps, and there is a $\delta$-correct algorithm for Best-$1$-Arm with sample complexity $O\left(H(I)\cdot\left(\ln\delta^{-1}+\mathsf{Ent}(I)\right)+\Delta_{[2]}^{-2}\ln\ln\Delta_{[2]}^{-1}\right)$. If the conjecture is true, we would have a complete understanding of the instance-wise sample complexity of Best-$1$-Arm. We make significant progress towards the resolution of the gap-entropy conjecture. For the upper bound, we provide a highly nontrivial algorithm which requires [O\left(H(I)\cdot\left(\ln\delta^{-1} +\mathsf{Ent}(I)\right)+\Delta_{[2]}^{-2}\ln\ln\Delta_{[2]}^{-1}\mathrm{polylog}(n,\delta^{-1})\right)] samples in expectation. For the lower bound, we show that for any Gaussian Best-$1$-Arm instance with gaps of the form $2^{-k}$, any $\delta$-correct monotone algorithm requires $\Omega\left(H(I)\cdot\left(\ln\delta^{-1} + \mathsf{Ent}(I)\right)\right)$ samples in expectation.
Tasks
Published	2016-08-22
URL	http://arxiv.org/abs/1608.06031v2
PDF	http://arxiv.org/pdf/1608.06031v2.pdf
PWC	https://paperswithcode.com/paper/towards-instance-optimal-bounds-for-best-arm
Repo
Framework

AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Games


Title	AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Games
Authors	Neil Burch, Martin Schmid, Matej Moravčík, Michael Bowling
Abstract	Evaluating agent performance when outcomes are stochastic and agents use randomized strategies can be challenging when there is limited data available. The variance of sampled outcomes may make the simple approach of Monte Carlo sampling inadequate. This is the case for agents playing heads-up no-limit Texas hold’em poker, where man-machine competitions have involved multiple days of consistent play and still not resulted in statistically significant conclusions even when the winner’s margin is substantial. In this paper, we introduce AIVAT, a low variance, provably unbiased value assessment tool that uses an arbitrary heuristic estimate of state value, as well as the explicit strategy of a subset of the agents. Unlike existing techniques which reduce the variance from chance events, or only consider game ending actions, AIVAT reduces the variance both from choices by nature and by players with a known strategy. The resulting estimator in no-limit poker can reduce the number of hands needed to draw statistical conclusions by more than a factor of 10.
Tasks
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06915v2
PDF	http://arxiv.org/pdf/1612.06915v2.pdf
PWC	https://paperswithcode.com/paper/aivat-a-new-variance-reduction-technique-for
Repo
Framework

Multi-Object Reasoning with Constrained Goal Models


Title	Multi-Object Reasoning with Constrained Goal Models
Authors	Chi Mai Nguyen, Roberto Sebastiani, Paolo Giorgini, John Mylopoulos
Abstract	Goal models have been widely used in Computer Science to represent software requirements, business objectives, and design qualities. Existing goal modelling techniques, however, have shown limitations of expressiveness and/or tractability in coping with complex real-world problems. In this work, we exploit advances in automated reasoning technologies, notably Satisfiability and Optimization Modulo Theories (SMT/OMT), and we propose and formalize: (i) an extended modelling language for goals, namely the Constrained Goal Model (CGM), which makes explicit the notion of goal refinement and of domain assumption, allows for expressing preferences between goals and refinements, and allows for associating numerical attributes to goals and refinements for defining constraints and optimization goals over multiple objective functions, refinements and their numerical attributes; (ii) a novel set of automated reasoning functionalities over CGMs, allowing for automatically generating suitable refinements of input CGMs, under user-specified assumptions and constraints, that also maximize preferences and optimize given objective functions. We have implemented these modelling and reasoning functionalities in a tool, named CGM-Tool, using the OMT solver OptiMathSAT as automated reasoning backend. Moreover, we have conducted an experimental evaluation on large CGMs to support the claim that our proposal scales well for goal models with thousands of elements.
Tasks
Published	2016-01-27
URL	http://arxiv.org/abs/1601.07409v2
PDF	http://arxiv.org/pdf/1601.07409v2.pdf
PWC	https://paperswithcode.com/paper/multi-object-reasoning-with-constrained-goal
Repo
Framework

Learning Sparse, Distributed Representations using the Hebbian Principle


Title	Learning Sparse, Distributed Representations using the Hebbian Principle
Authors	Aseem Wadhwa, Upamanyu Madhow
Abstract	The “fire together, wire together” Hebbian model is a central principle for learning in neuroscience, but surprisingly, it has found limited applicability in modern machine learning. In this paper, we take a first step towards bridging this gap, by developing flavors of competitive Hebbian learning which produce sparse, distributed neural codes using online adaptation with minimal tuning. We propose an unsupervised algorithm, termed Adaptive Hebbian Learning (AHL). We illustrate the distributed nature of the learned representations via output entropy computations for synthetic data, and demonstrate superior performance, compared to standard alternatives such as autoencoders, in training a deep convolutional net on standard image datasets.
Tasks
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04228v1
PDF	http://arxiv.org/pdf/1611.04228v1.pdf
PWC	https://paperswithcode.com/paper/learning-sparse-distributed-representations
Repo
Framework

Super-Resolved Retinal Image Mosaicing


Title	Super-Resolved Retinal Image Mosaicing
Authors	Thomas Köhler, Axel Heinrich, Andreas Maier, Joachim Hornegger, Ralf P. Tornow
Abstract	The acquisition of high-resolution retinal fundus images with a large field of view (FOV) is challenging due to technological, physiological and economic reasons. This paper proposes a fully automatic framework to reconstruct retinal images of high spatial resolution and increased FOV from multiple low-resolution images captured with non-mydriatic, mobile and video-capable but low-cost cameras. Within the scope of one examination, we scan different regions on the retina by exploiting eye motion conducted by a patient guidance. Appropriate views for our mosaicing method are selected based on optic disk tracking to trace eye movements. For each view, one super-resolved image is reconstructed by fusion of multiple video frames. Finally, all super-resolved views are registered to a common reference using a novel polynomial registration scheme and combined by means of image mosaicing. We evaluated our framework for a mobile and low-cost video fundus camera. In our experiments, we reconstructed retinal images of up to 30{\deg} FOV from 10 complementary views of 15{\deg} FOV. An evaluation of the mosaics by human experts as well as a quantitative comparison to conventional color fundus images encourage the clinical usability of our framework.
Tasks
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03458v1
PDF	http://arxiv.org/pdf/1602.03458v1.pdf
PWC	https://paperswithcode.com/paper/super-resolved-retinal-image-mosaicing
Repo
Framework

A single scale retinex based method for palm vein extraction


Title	A single scale retinex based method for palm vein extraction
Authors	Chongyang Wang, Ming Peng, Lingfeng Xu, Tong Chen
Abstract	Palm vein recognition is a novel biometric identification technology. But how to gain a better vein extraction result from the raw palm image is still a challenging problem, especially when the raw data collection has the problem of asymmetric illumination. This paper proposes a method based on single scale Retinex algorithm to extract palm vein image when strong shadow presents due to asymmetric illumination and uneven geometry of the palm. We test our method on a multispectral palm image. The experimental result shows that the proposed method is robust to the influence of illumination angle and shadow. Compared to the traditional extraction methods, the proposed method can obtain palm vein lines with better visualization performance (the contrast ratio increases by 18.4%, entropy increases by 1.07%, and definition increases by 18.8%).
Tasks
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08154v1
PDF	http://arxiv.org/pdf/1605.08154v1.pdf
PWC	https://paperswithcode.com/paper/a-single-scale-retinex-based-method-for-palm
Repo
Framework

Reliably Learning the ReLU in Polynomial Time


Title	Reliably Learning the ReLU in Polynomial Time
Authors	Surbhi Goel, Varun Kanade, Adam Klivans, Justin Thaler
Abstract	We give the first dimension-efficient algorithms for learning Rectified Linear Units (ReLUs), which are functions of the form $\mathbf{x} \mapsto \max(0, \mathbf{w} \cdot \mathbf{x})$ with $\mathbf{w} \in \mathbb{S}^{n-1}$. Our algorithm works in the challenging Reliable Agnostic learning model of Kalai, Kanade, and Mansour (2009) where the learner is given access to a distribution $\cal{D}$ on labeled examples but the labeling may be arbitrary. We construct a hypothesis that simultaneously minimizes the false-positive rate and the loss on inputs given positive labels by $\cal{D}$, for any convex, bounded, and Lipschitz loss function. The algorithm runs in polynomial-time (in $n$) with respect to any distribution on $\mathbb{S}^{n-1}$ (the unit sphere in $n$ dimensions) and for any error parameter $\epsilon = \Omega(1/\log n)$ (this yields a PTAS for a question raised by F. Bach on the complexity of maximizing ReLUs). These results are in contrast to known efficient algorithms for reliably learning linear threshold functions, where $\epsilon$ must be $\Omega(1)$ and strong assumptions are required on the marginal distribution. We can compose our results to obtain the first set of efficient algorithms for learning constant-depth networks of ReLUs. Our techniques combine kernel methods and polynomial approximations with a “dual-loss” approach to convex programming. As a byproduct we obtain a number of applications including the first set of efficient algorithms for “convex piecewise-linear fitting” and the first efficient algorithms for noisy polynomial reconstruction of low-weight polynomials on the unit sphere.
Tasks
Published	2016-11-30
URL	http://arxiv.org/abs/1611.10258v1
PDF	http://arxiv.org/pdf/1611.10258v1.pdf
PWC	https://paperswithcode.com/paper/reliably-learning-the-relu-in-polynomial-time
Repo
Framework

Sorting out typicality with the inverse moment matrix SOS polynomial


Title	Sorting out typicality with the inverse moment matrix SOS polynomial
Authors	Jean-Bernard Lasserre, Edouard Pauwels
Abstract	We study a surprising phenomenon related to the representation of a cloud of data points using polynomials. We start with the previously unnoticed empirical observation that, given a collection (a cloud) of data points, the sublevel sets of a certain distinguished polynomial capture the shape of the cloud very accurately. This distinguished polynomial is a sum-of-squares (SOS) derived in a simple manner from the inverse of the empirical moment matrix. In fact, this SOS polynomial is directly related to orthogonal polynomials and the Christoffel function. This allows to generalize and interpret extremality properties of orthogonal polynomials and to provide a mathematical rationale for the observed phenomenon. Among diverse potential applications, we illustrate the relevance of our results on a network intrusion detection task for which we obtain performances similar to existing dedicated methods reported in the literature.
Tasks	Intrusion Detection, Network Intrusion Detection
Published	2016-06-13
URL	http://arxiv.org/abs/1606.03858v2
PDF	http://arxiv.org/pdf/1606.03858v2.pdf
PWC	https://paperswithcode.com/paper/sorting-out-typicality-with-the-inverse
Repo
Framework

Removal of Batch Effects using Distribution-Matching Residual Networks


Title	Removal of Batch Effects using Distribution-Matching Residual Networks
Authors	Uri Shaham, Kelly P. Stanton, Jun Zhao, Huamin Li, Khadir Raddassi, Ruth Montgomery, Yuval Kluger
Abstract	Sources of variability in experimentally derived data include measurement error in addition to the physical phenomena of interest. This measurement error is a combination of systematic components, originating from the measuring instrument, and random measurement errors. Several novel biological technologies, such as mass cytometry and single-cell RNA-seq, are plagued with systematic errors that may severely affect statistical analysis if the data is not properly calibrated. We propose a novel deep learning approach for removing systematic batch effects. Our method is based on a residual network, trained to minimize the Maximum Mean Discrepancy (MMD) between the multivariate distributions of two replicates, measured in different batches. We apply our method to mass cytometry and single-cell RNA-seq datasets, and demonstrate that it effectively attenuates batch effects.
Tasks
Published	2016-10-13
URL	http://arxiv.org/abs/1610.04181v6
PDF	http://arxiv.org/pdf/1610.04181v6.pdf
PWC	https://paperswithcode.com/paper/removal-of-batch-effects-using-distribution
Repo
Framework

A Unified Computational and Statistical Framework for Nonconvex Low-Rank Matrix Estimation


Title	A Unified Computational and Statistical Framework for Nonconvex Low-Rank Matrix Estimation
Authors	Lingxiao Wang, Xiao Zhang, Quanquan Gu
Abstract	We propose a unified framework for estimating low-rank matrices through nonconvex optimization based on gradient descent algorithm. Our framework is quite general and can be applied to both noisy and noiseless observations. In the general case with noisy observations, we show that our algorithm is guaranteed to linearly converge to the unknown low-rank matrix up to minimax optimal statistical error, provided an appropriate initial estimator. While in the generic noiseless setting, our algorithm converges to the unknown low-rank matrix at a linear rate and enables exact recovery with optimal sample complexity. In addition, we develop a new initialization algorithm to provide a desired initial estimator, which outperforms existing initialization algorithms for nonconvex low-rank matrix estimation. We illustrate the superiority of our framework through three examples: matrix regression, matrix completion, and one-bit matrix completion. We also corroborate our theory through extensive experiments on synthetic data.
Tasks	Matrix Completion
Published	2016-10-17
URL	http://arxiv.org/abs/1610.05275v1
PDF	http://arxiv.org/pdf/1610.05275v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-computational-and-statistical
Repo
Framework