October 18, 2019

3033 words 15 mins read

Paper Group ANR 654

Image Posterization Using Fuzzy Logic and Bilateral Filter. Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks. Superconducting Optoelectronic Neurons V: Networks and Scaling. CAB: Continuous Adaptive Blending Estimator for Policy Evaluation and Learning. Quality Classified Image Analysis with Application t …

Image Posterization Using Fuzzy Logic and Bilateral Filter


Title	Image Posterization Using Fuzzy Logic and Bilateral Filter
Authors	Mahmoud Afifi
Abstract	Image posterization is converting images with a large number of tones into synthetic images with distinct flat areas and a fewer number of tones. In this technical report, we present the implementation and results of using fuzzy logic in order to generate a posterized image in a simple and fast way. The image filter is based on fuzzy logic and bilateral filtering; where, the given image is blurred to remove small details. Then, the fuzzy logic is used to classify each pixel into one of three specific categories in order to reduce the number of colors. This filter was developed during building the Specs on Face dataset in order to add a new level of difficulty to the original face images in the dataset. This filter does not hurt the human detection performance; however, it is considered a hindrance evading the face detection process. This filter can be used generally for posterizing images, especially those have a high contrast to get images with vivid colors.
Tasks	Face Detection, Human Detection
Published	2018-02-03
URL	http://arxiv.org/abs/1802.01009v1
PDF	http://arxiv.org/pdf/1802.01009v1.pdf
PWC	https://paperswithcode.com/paper/image-posterization-using-fuzzy-logic-and
Repo
Framework

Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks


Title	Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks
Authors	Sepidehsadat Hosseini, Seok Hee Lee, Nam Ik Cho
Abstract	Since the convolutional neural network (CNN) is be- lieved to find right features for a given problem, the study of hand-crafted features is somewhat neglected these days. In this paper, we show that finding an appropriate feature for the given problem may be still important as they can en- hance the performance of CNN-based algorithms. Specif- ically, we show that feeding an appropriate feature to the CNN enhances its performance in some face related works such as age/gender estimation, face detection and emotion recognition. We use Gabor filter bank responses for these tasks, feeding them to the CNN along with the input image. The stack of image and Gabor responses can be fed to the CNN as a tensor input, or as a fused image which is a weighted sum of image and Gabor responses. The Gabor filter parameters can also be tuned depending on the given problem, for increasing the performance. From the extensive experiments, it is shown that the proposed methods provide better performance than the conventional CNN-based methods that use only the input images.
Tasks	Emotion Recognition, Face Detection
Published	2018-01-24
URL	http://arxiv.org/abs/1801.07848v1
PDF	http://arxiv.org/pdf/1801.07848v1.pdf
PWC	https://paperswithcode.com/paper/feeding-hand-crafted-features-for-enhancing
Repo
Framework

Superconducting Optoelectronic Neurons V: Networks and Scaling


Title	Superconducting Optoelectronic Neurons V: Networks and Scaling
Authors	Jeffrey M. Shainline, Jeff Chiles, Sonia M. Buckley, Adam N. McCaughan, Richard P. Mirin, Sae Woo Nam
Abstract	Networks of superconducting optoelectronic neurons are investigated for their near-term technological potential and long-term physical limitations. Networks with short average path length, high clustering coefficient, and power-law degree distribution are designed using a growth model that assigns connections between new and existing nodes based on spatial distance as well as degree of existing nodes. The network construction algorithm is scalable to arbitrary levels of network hierarchy and achieves systems with fractal spatial properties and efficient wiring. By modeling the physical size of superconducting optoelectronic neurons, we calculate the area of these networks. A system with 8100 neurons and 330,430 total synapses will fit on a 1,cm $\times$ 1,cm die. Systems of millions of neurons with hundreds of millions of synapses will fit on a 300,mm wafer. For multi-wafer assemblies, communication at light speed enables a neuronal pool the size of a large data center comprising 100 trillion neurons with coherent oscillations at 1,MHz. Assuming a power law frequency distribution, as is necessary for self-organized criticality, we calculate the power consumption of the networks. We find the use of single photons for communication and superconducting circuits for computation leads to power density low enough to be cooled by liquid $^4$He for networks of any scale.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01942v3
PDF	http://arxiv.org/pdf/1805.01942v3.pdf
PWC	https://paperswithcode.com/paper/superconducting-optoelectronic-neurons-v
Repo
Framework

CAB: Continuous Adaptive Blending Estimator for Policy Evaluation and Learning


Title	CAB: Continuous Adaptive Blending Estimator for Policy Evaluation and Learning
Authors	Yi Su, Lequn Wang, Michele Santacatterina, Thorsten Joachims
Abstract	The ability to perform offline A/B-testing and off-policy learning using logged contextual bandit feedback is highly desirable in a broad range of applications, including recommender systems, search engines, ad placement, and personalized health care. Both offline A/B-testing and off-policy learning require a counterfactual estimator that evaluates how some new policy would have performed, if it had been used instead of the logging policy. In this paper, we identify a family of counterfactual estimators which subsumes most such estimators proposed to date. Our analysis of this family identifies a new estimator - called Continuous Adaptive Blending (CAB) - which enjoys many advantageous theoretical and practical properties. In particular, it can be substantially less biased than clipped Inverse Propensity Score (IPS) weighting and the Direct Method, and it can have less variance than Doubly Robust and IPS estimators. In addition, it is sub-differentiable such that it can be used for learning, unlike the SWITCH estimator. Experimental results show that CAB provides excellent evaluation accuracy and outperforms other counterfactual estimators in terms of learning performance.
Tasks	Recommendation Systems
Published	2018-11-06
URL	https://arxiv.org/abs/1811.02672v4
PDF	https://arxiv.org/pdf/1811.02672v4.pdf
PWC	https://paperswithcode.com/paper/cab-continuous-adaptive-blending-estimator
Repo
Framework

Quality Classified Image Analysis with Application to Face Detection and Recognition


Title	Quality Classified Image Analysis with Application to Face Detection and Recognition
Authors	Fei Yang, Qian Zhang, Miaohui Wang, Guoping Qiu
Abstract	Motion blur, out of focus, insufficient spatial resolution, lossy compression and many other factors can all cause an image to have poor quality. However, image quality is a largely ignored issue in traditional pattern recognition literature. In this paper, we use face detection and recognition as case studies to show that image quality is an essential factor which will affect the performances of traditional algorithms. We demonstrated that it is not the image quality itself that is the most important, but rather the quality of the images in the training set should have similar quality as those in the testing set. To handle real-world application scenarios where images with different kinds and severities of degradation can be presented to the system, we have developed a quality classified image analysis framework to deal with images of mixed qualities adaptively. We use deep neural networks first to classify images based on their quality classes and then design a separate face detector and recognizer for images in each quality class. We will present experimental results to show that our quality classified framework can accurately classify images based on the type and severity of image degradations and can significantly boost the performances of state-of-the-art face detector and recognizer in dealing with image datasets containing mixed quality images.
Tasks	Face Detection
Published	2018-01-19
URL	http://arxiv.org/abs/1801.06445v1
PDF	http://arxiv.org/pdf/1801.06445v1.pdf
PWC	https://paperswithcode.com/paper/quality-classified-image-analysis-with
Repo
Framework

Automatic Skin Lesion Segmentation Using GrabCut in HSV Colour Space


Title	Automatic Skin Lesion Segmentation Using GrabCut in HSV Colour Space
Authors	Fakrul Islam Tushar
Abstract	Skin lesion segmentation is one of the first steps towards automatic Computer-Aided Diagnosis of skin cancer. Vast variety in the appearance of the skin lesion makes this task very challenging. The contribution of this paper is to apply a power foreground extraction technique called GrabCut for automatic skin lesion segmentation with minimal human interaction in HSV color space. Preprocessing was performed for removing the outer black border. Jaccard Index was measured to evaluate the performance of the segmentation method. On average, 0.71 Jaccard Index was achieved on 1000 images from ISIC challenge 2017 Training Dataset.
Tasks	Lesion Segmentation
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00871v1
PDF	http://arxiv.org/pdf/1810.00871v1.pdf
PWC	https://paperswithcode.com/paper/automatic-skin-lesion-segmentation-using-1
Repo
Framework

A Single Shot Text Detector with Scale-adaptive Anchors


Title	A Single Shot Text Detector with Scale-adaptive Anchors
Authors	Qi Yuan, Bingwang Zhang, Haojie Li, Zhihui Wang, Zhongxuan Luo
Abstract	Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances. They usually rely on a large amount of anchors with different scales to discover texts in scene images, thus leading to high computational cost. In this paper, we propose an end-to-end box-based text detector with scale-adaptive anchors, which can dynamically adjust the scales of anchors according to the sizes of underlying texts by introducing an additional scale regression layer. The proposed scale-adaptive anchors allow us to use a few number of anchors to handle multi-scale texts and therefore significantly improve the computational efficiency. Moreover, compared to discrete scales used in previous methods, the learned continuous scales are more reliable, especially for small texts detection. Additionally, we propose Anchor convolution to better exploit necessary feature information by dynamically adjusting the sizes of receptive fields according to the learned scales. Extensive experiments demonstrate that the proposed detector is fast, taking only $0.28$ second per image, while outperforming most state-of-the-art methods in accuracy.
Tasks
Published	2018-07-05
URL	http://arxiv.org/abs/1807.01884v1
PDF	http://arxiv.org/pdf/1807.01884v1.pdf
PWC	https://paperswithcode.com/paper/a-single-shot-text-detector-with-scale
Repo
Framework

Exact partial information decompositions for Gaussian systems based on dependency constraints


Title	Exact partial information decompositions for Gaussian systems based on dependency constraints
Authors	James W. Kay, Robin A. A. Ince
Abstract	The Partial Information Decomposition (PID) [arXiv:1004.2515] provides a theoretical framework to characterize and quantify the structure of multivariate information sharing. A new method (Idep) has recently been proposed for computing a two-predictor PID over discrete spaces. [arXiv:1709.06653] A lattice of maximum entropy probability models is constructed based on marginal dependency constraints, and the unique information that a particular predictor has about the target is defined as the minimum increase in joint predictor-target mutual information when that particular predictor-target marginal dependency is constrained. Here, we apply the Idep approach to Gaussian systems, for which the marginally constrained maximum entropy models are Gaussian graphical models. Closed form solutions for the Idep PID are derived for both univariate and multivariate Gaussian systems. Numerical and graphical illustrations are provided, together with practical and theoretical comparisons of the Idep PID with the minimum mutual information PID (Immi). [arXiv:1411.2832] In particular, it is proved that the Immi method generally produces larger estimates of redundancy and synergy than does the Idep method. In discussion of the practical examples, the PIDs are complemented by the use of deviance tests for the comparison of Gaussian graphical models.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02030v1
PDF	http://arxiv.org/pdf/1803.02030v1.pdf
PWC	https://paperswithcode.com/paper/exact-partial-information-decompositions-for
Repo
Framework

Bayes-optimal Hierarchical Classification over Asymmetric Tree-Distance Loss


Title	Bayes-optimal Hierarchical Classification over Asymmetric Tree-Distance Loss
Authors	Dheeraj Mekala, Vivek Gupta, Purushottam Kar, Harish Karnick
Abstract	Hierarchical classification is supervised multi-class classification problem over the set of class labels organized according to a hierarchy. In this report, we study the work by Ramaswamy et. al. on hierarchical classification over symmetric tree distance loss. We extend the consistency of hierarchical classification algorithm over asymmetric tree distance loss. We design a $\mathcal{O}(nk\log{}n)$ algorithm to find Bayes optimal classification for a k-ary tree as a hierarchy. We show that under reasonable assumptions over asymmetric loss function, the Bayes optimal classification over this asymmetric loss can be found in $\mathcal{O}(k\log{}n)$. We exploit this insight and attempt to extend the Ova-Cascade algorithm \citet{ramaswamy2015convex} for hierarchical classification over the asymmetric loss.
Tasks
Published	2018-02-17
URL	http://arxiv.org/abs/1802.06771v1
PDF	http://arxiv.org/pdf/1802.06771v1.pdf
PWC	https://paperswithcode.com/paper/bayes-optimal-hierarchical-classification
Repo
Framework

Deep Ptych: Subsampled Fourier Ptychography using Generative Priors


Title	Deep Ptych: Subsampled Fourier Ptychography using Generative Priors
Authors	Fahad Shamshad, Farwa Abbas, Ali Ahmed
Abstract	This paper proposes a novel framework to regularize the highly ill-posed and non-linear Fourier ptychography problem using generative models. We demonstrate experimentally that our proposed algorithm, Deep Ptych, outperforms the existing Fourier ptychography techniques, in terms of quality of reconstruction and robustness against noise, using far fewer samples. We further modify the proposed approach to allow the generative model to explore solutions outside the range, leading to improved performance.
Tasks
Published	2018-12-22
URL	http://arxiv.org/abs/1812.11065v1
PDF	http://arxiv.org/pdf/1812.11065v1.pdf
PWC	https://paperswithcode.com/paper/deep-ptych-subsampled-fourier-ptychography
Repo
Framework

Adversarial Imitation via Variational Inverse Reinforcement Learning


Title	Adversarial Imitation via Variational Inverse Reinforcement Learning
Authors	Ahmed H. Qureshi, Byron Boots, Michael C. Yip
Abstract	We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy inverse reinforcement learning to learn near-optimal rewards and policies. Empowerment-based regularization prevents the policy from overfitting to expert demonstrations, which advantageously leads to more generalized behaviors that result in learning near-optimal rewards. Our method simultaneously learns empowerment through variational information maximization along with the reward and policy under the adversarial learning formulation. We evaluate our approach on various high-dimensional complex control tasks. We also test our learned rewards in challenging transfer learning problems where training and testing environments are made to be different from each other in terms of dynamics or structure. The results show that our proposed method not only learns near-optimal rewards and policies that are matching expert behavior but also performs significantly better than state-of-the-art inverse reinforcement learning algorithms.
Tasks	Transfer Learning
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06404v3
PDF	http://arxiv.org/pdf/1809.06404v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-imitation-via-variational-inverse
Repo
Framework

A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series


Title	A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series
Authors	Thomas Hollis, Antoine Viscardi, Seung Eun Yi
Abstract	While LSTMs show increasingly promising results for forecasting Financial Time Series (FTS), this paper seeks to assess if attention mechanisms can further improve performance. The hypothesis is that attention can help prevent long-term dependencies experienced by LSTM models. To test this hypothesis, the main contribution of this paper is the implementation of an LSTM with attention. Both the benchmark LSTM and the LSTM with attention were compared and both achieved reasonable performances of up to 60% on five stocks from Kaggle’s Two Sigma dataset. This comparative analysis demonstrates that an LSTM with attention can indeed outperform standalone LSTMs but further investigation is required as issues do arise with such model architectures.
Tasks	Time Series
Published	2018-12-18
URL	http://arxiv.org/abs/1812.07699v1
PDF	http://arxiv.org/pdf/1812.07699v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-lstms-and-attention
Repo
Framework

Modified Diversity of Class Probability Estimation Co-training for Hyperspectral Image Classification


Title	Modified Diversity of Class Probability Estimation Co-training for Hyperspectral Image Classification
Authors	Yan Ju, Lingling Li, Licheng Jiao, Zhongle Ren, Biao Hou, Shuyuan Yang
Abstract	Due to the limited amount and imbalanced classes of labeled training data, the conventional supervised learning can not ensure the discrimination of the learned feature for hyperspectral image (HSI) classification. In this paper, we propose a modified diversity of class probability estimation (MDCPE) with two deep neural networks to learn spectral-spatial feature for HSI classification. In co-training phase, recurrent neural network (RNN) and convolutional neural network (CNN) are utilized as two learners to extract features from labeled and unlabeled data. Based on the extracted features, MDCPE selects most credible samples to update initial labeled data by combining k-means clustering with the traditional diversity of class probability estimation (DCPE) co-training. In this way, MDCPE can keep new labeled data class-balanced and extract discriminative features for both the minority and majority classes. During testing process, classification results are acquired by co-decision of the two learners. Experimental results demonstrate that the proposed semi-supervised co-training method can make full use of unlabeled information to enhance generality of the learners and achieve favorable accuracies on all three widely used data sets: Salinas, Pavia University and Pavia Center.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01436v1
PDF	http://arxiv.org/pdf/1809.01436v1.pdf
PWC	https://paperswithcode.com/paper/modified-diversity-of-class-probability
Repo
Framework

Random matrix-improved estimation of covariance matrix distances


Title	Random matrix-improved estimation of covariance matrix distances
Authors	Romain Couillet, Malik Tiomoko, Steeve Zozor, Eric Moisan
Abstract	Given two sets $x_1^{(1)},\ldots,x_{n_1}^{(1)}$ and $x_1^{(2)},\ldots,x_{n_2}^{(2)}\in\mathbb{R}^p$ (or $\mathbb{C}^p$) of random vectors with zero mean and positive definite covariance matrices $C_1$ and $C_2\in\mathbb{R}^{p\times p}$ (or $\mathbb{C}^{p\times p}$), respectively, this article provides novel estimators for a wide range of distances between $C_1$ and $C_2$ (along with divergences between some zero mean and covariance $C_1$ or $C_2$ probability measures) of the form $\frac1p\sum_{i=1}^n f(\lambda_i(C_1^{-1}C_2))$ (with $\lambda_i(X)$ the eigenvalues of matrix $X$). These estimators are derived using recent advances in the field of random matrix theory and are asymptotically consistent as $n_1,n_2,p\to\infty$ with non trivial ratios $p/n_1<1$ and $p/n_2<1$ (the case $p/n_2>1$ is also discussed). A first “generic” estimator, valid for a large set of $f$ functions, is provided under the form of a complex integral. Then, for a selected set of $f$'s of practical interest (namely, $f(t)=t$, $f(t)=\log(t)$, $f(t)=\log(1+st)$ and $f(t)=\log^2(t)$), a closed-form expression is provided. Beside theoretical findings, simulation results suggest an outstanding performance advantage for the proposed estimators when compared to the classical “plug-in” estimator $\frac1p\sum_{i=1}^n f(\lambda_i(\hat C_1^{-1}\hat C_2))$ (with $\hat C_a=\frac1{n_a}\sum_{i=1}^{n_a}x_i^{(a)}x_i^{(a){\sf T}}$), and this even for very small values of $n_1,n_2,p$.
Tasks
Published	2018-10-10
URL	http://arxiv.org/abs/1810.04534v1
PDF	http://arxiv.org/pdf/1810.04534v1.pdf
PWC	https://paperswithcode.com/paper/random-matrix-improved-estimation-of
Repo
Framework

A Survey on Surrogate Approaches to Non-negative Matrix Factorization


Title	A Survey on Surrogate Approaches to Non-negative Matrix Factorization
Authors	Pascal Fernsel, Peter Maass
Abstract	Motivated by applications in hyperspectral imaging we investigate methods for approximating a high-dimensional non-negative matrix $\mathbf{\mathit{Y}}$ by a product of two lower-dimensional, non-negative matrices $\mathbf{\mathit{K}}$ and $\mathbf{\mathit{X}}.$ This so-called non-negative matrix factorization is based on defining suitable Tikhonov functionals, which combine a discrepancy measure for $\mathbf{\mathit{Y}}\approx\mathbf{\mathit{KX}}$ with penalty terms for enforcing additional properties of $\mathbf{\mathit{K}}$ and $\mathbf{\mathit{X}}$. The minimization is based on alternating minimization with respect to $\mathbf{\mathit{K}}$ or $\mathbf{\mathit{X}}$, where in each iteration step one replaces the original Tikhonov functional by a locally defined surrogate functional. The choice of surrogate functionals is crucial: It should allow a comparatively simple minimization and simultaneously its first order optimality condition should lead to multiplicative update rules, which automatically preserve non-negativity of the iterates. We review the most standard construction principles for surrogate functionals for Frobenius-norm and Kullback-Leibler discrepancy measures. We extend the known surrogate constructions by a general framework, which allows to add a large variety of penalty terms. The paper finishes by deriving the corresponding alternating minimization schemes explicitely and by applying these methods to MALDI imaging data.
Tasks
Published	2018-08-06
URL	http://arxiv.org/abs/1808.01975v2
PDF	http://arxiv.org/pdf/1808.01975v2.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-surrogate-approaches-to-non
Repo
Framework