May 7, 2019

3350 words 16 mins read

Paper Group ANR 113

Kernel-based Reconstruction of Graph Signals. Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator. A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment. Using Indirect Encoding of Multiple Brains to Produce Multimodal Behavior. Enhanced Boolean Correlation Matrix Memory. Tuning the …

Kernel-based Reconstruction of Graph Signals


Title	Kernel-based Reconstruction of Graph Signals
Authors	Daniel Romero, Meng Ma, Georgios B. Giannakis
Abstract	A number of applications in engineering, social sciences, physics, and biology involve inference over networks. In this context, graph signals are widely encountered as descriptors of vertex attributes or features in graph-structured data. Estimating such signals in all vertices given noisy observations of their values on a subset of vertices has been extensively analyzed in the literature of signal processing on graphs (SPoG). This paper advocates kernel regression as a framework generalizing popular SPoG modeling and reconstruction and expanding their capabilities. Formulating signal reconstruction as a regression task on reproducing kernel Hilbert spaces of graph signals permeates benefits from statistical learning, offers fresh insights, and allows for estimators to leverage richer forms of prior information than existing alternatives. A number of SPoG notions such as bandlimitedness, graph filters, and the graph Fourier transform are naturally accommodated in the kernel framework. Additionally, this paper capitalizes on the so-called representer theorem to devise simpler versions of existing Thikhonov regularized estimators, and offers a novel probabilistic interpretation of kernel methods on graphs based on graphical models. Motivated by the challenges of selecting the bandwidth parameter in SPoG estimators or the kernel map in kernel-based methods, the present paper further proposes two multi-kernel approaches with complementary strengths. Whereas the first enables estimation of the unknown bandwidth of bandlimited signals, the second allows for efficient graph filter selection. Numerical tests with synthetic as well as real data demonstrate the merits of the proposed methods relative to state-of-the-art alternatives.
Tasks
Published	2016-05-23
URL	http://arxiv.org/abs/1605.07174v1
PDF	http://arxiv.org/pdf/1605.07174v1.pdf
PWC	https://paperswithcode.com/paper/kernel-based-reconstruction-of-graph-signals
Repo
Framework

Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator


Title	Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator
Authors	Hossein Ziaei Nafchi, Atena Shahkolaei, Rachid Hedjam, Mohamed Cheriet
Abstract	Applications of perceptual image quality assessment (IQA) in image and video processing, such as image acquisition, image compression, image restoration and multimedia communication, have led to the development of many IQA metrics. In this paper, a reliable full reference IQA model is proposed that utilize gradient similarity (GS), chromaticity similarity (CS), and deviation pooling (DP). By considering the shortcomings of the commonly used GS to model human visual system (HVS), a new GS is proposed through a fusion technique that is more likely to follow HVS. We propose an efficient and effective formulation to calculate the joint similarity map of two chromatic channels for the purpose of measuring color changes. In comparison with a commonly used formulation in the literature, the proposed CS map is shown to be more efficient and provide comparable or better quality predictions. Motivated by a recent work that utilizes the standard deviation pooling, a general formulation of the DP is presented in this paper and used to compute a final score from the proposed GS and CS maps. This proposed formulation of DP benefits from the Minkowski pooling and a proposed power pooling as well. The experimental results on six datasets of natural images, a synthetic dataset, and a digitally retouched dataset show that the proposed index provides comparable or better quality predictions than the most recent and competing state-of-the-art IQA metrics in the literature, it is reliable and has low complexity. The MATLAB source code of the proposed metric is available at https://www.mathworks.com/matlabcentral/fileexchange/59809.
Tasks	Image Compression, Image Quality Assessment, Image Restoration
Published	2016-08-26
URL	http://arxiv.org/abs/1608.07433v4
PDF	http://arxiv.org/pdf/1608.07433v4.pdf
PWC	https://paperswithcode.com/paper/mean-deviation-similarity-index-efficient-and
Repo
Framework

A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment


Title	A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment
Authors	Rafael Reisenhofer, Sebastian Bosse, Gitta Kutyniok, Thomas Wiegand
Abstract	In most practical situations, the compression or transmission of images and videos creates distortions that will eventually be perceived by a human observer. Vice versa, image and video restoration techniques, such as inpainting or denoising, aim to enhance the quality of experience of human viewers. Correctly assessing the similarity between an image and an undistorted reference image as subjectively experienced by a human viewer can thus lead to significant improvements in any transmission, compression, or restoration system. This paper introduces the Haar wavelet-based perceptual similarity index (HaarPSI), a novel and computationally inexpensive similarity measure for full reference image quality assessment. The HaarPSI utilizes the coefficients obtained from a Haar wavelet decomposition to assess local similarities between two images, as well as the relative importance of image areas. The consistency of the HaarPSI with the human quality of experience was validated on four large benchmark databases containing thousands of differently distorted images. On these databases, the HaarPSI achieves higher correlations with human opinion scores than state-of-the-art full reference similarity measures like the structural similarity index (SSIM), the feature similarity index (FSIM), and the visual saliency-based index (VSI). Along with the simple computational structure and the short execution time, these experimental results suggest a high applicability of the HaarPSI in real world tasks.
Tasks	Denoising, Image Quality Assessment
Published	2016-07-20
URL	http://arxiv.org/abs/1607.06140v4
PDF	http://arxiv.org/pdf/1607.06140v4.pdf
PWC	https://paperswithcode.com/paper/a-haar-wavelet-based-perceptual-similarity
Repo
Framework

Using Indirect Encoding of Multiple Brains to Produce Multimodal Behavior


Title	Using Indirect Encoding of Multiple Brains to Produce Multimodal Behavior
Authors	Jacob Schrum, Joel Lehman, Sebastian Risi
Abstract	An important challenge in neuroevolution is to evolve complex neural networks with multiple modes of behavior. Indirect encodings can potentially answer this challenge. Yet in practice, indirect encodings do not yield effective multimodal controllers. Thus, this paper introduces novel multimodal extensions to HyperNEAT, a popular indirect encoding. A previous multimodal HyperNEAT approach called situational policy geometry assumes that multiple brains benefit from being embedded within an explicit geometric space. However, experiments here illustrate that this assumption unnecessarily constrains evolution, resulting in lower performance. Specifically, this paper introduces HyperNEAT extensions for evolving many brains without assuming geometric relationships between them. The resulting Multi-Brain HyperNEAT can exploit human-specified task divisions to decide when each brain controls the agent, or can automatically discover when brains should be used, by means of preference neurons. A further extension called module mutation allows evolution to discover the number of brains, enabling multimodal behavior with even less expert knowledge. Experiments in several multimodal domains highlight that multi-brain approaches are more effective than HyperNEAT without multimodal extensions, and show that brains without a geometric relation to each other outperform situational policy geometry. The conclusion is that Multi-Brain HyperNEAT provides several promising techniques for evolving complex multimodal behavior.
Tasks
Published	2016-04-26
URL	http://arxiv.org/abs/1604.07806v1
PDF	http://arxiv.org/pdf/1604.07806v1.pdf
PWC	https://paperswithcode.com/paper/using-indirect-encoding-of-multiple-brains-to
Repo
Framework

Enhanced Boolean Correlation Matrix Memory


Title	Enhanced Boolean Correlation Matrix Memory
Authors	Mario Mastriani
Abstract	This paper introduces an Enhanced Boolean version of the Correlation Matrix Memory (CMM), which is useful to work with binary memories. A novel Boolean Orthonormalization Process (BOP) is presented to convert a non-orthonormal Boolean basis, i.e., a set of non-orthonormal binary vectors (in a Boolean sense) to an orthonormal Boolean basis, i.e., a set of orthonormal binary vectors (in a Boolean sense). This work shows that it is possible to improve the performance of Boolean CMM thanks BOP algorithm. Besides, the BOP algorithm has a lot of additional fields of applications, e.g.: Steganography, Hopfield Networks, Bi-level image processing, etc. Finally, it is important to mention that the BOP is an extremely stable and fast algorithm.
Tasks
Published	2016-07-11
URL	http://arxiv.org/abs/1607.04267v1
PDF	http://arxiv.org/pdf/1607.04267v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-boolean-correlation-matrix-memory
Repo
Framework

Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization


Title	Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization
Authors	Valentin Dalibard, Michael Schaarschmidt, Eiko Yoneki
Abstract	We present an optimizer which uses Bayesian optimization to tune the system parameters of distributed stochastic gradient descent (SGD). Given a specific context, our goal is to quickly find efficient configurations which appropriately balance the load between the available machines to minimize the average SGD iteration time. Our experiments consider setups with over thirty parameters. Traditional Bayesian optimization, which uses a Gaussian process as its model, is not well suited to such high dimensional domains. To reduce convergence time, we exploit the available structure. We design a probabilistic model which simulates the behavior of distributed SGD and use it within Bayesian optimization. Our model can exploit many runtime measurements for inference per evaluation of the objective function. Our experiments show that our resulting optimizer converges to efficient configurations within ten iterations, the optimized configurations outperform those found by generic optimizer in thirty iterations by up to 2X.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00383v1
PDF	http://arxiv.org/pdf/1612.00383v1.pdf
PWC	https://paperswithcode.com/paper/tuning-the-scheduling-of-distributed
Repo
Framework


Title	Towards using social media to identify individuals at risk for preventable chronic illness
Authors	Dane Bell, Daniel Fried, Luwen Huangfu, Mihai Surdeanu, Stephen Kobourov
Abstract	We describe a strategy for the acquisition of training data necessary to build a social-media-driven early detection system for individuals at risk for (preventable) type 2 diabetes mellitus (T2DM). The strategy uses a game-like quiz with data and questions acquired semi-automatically from Twitter. The questions are designed to inspire participant engagement and collect relevant data to train a public-health model applied to individuals. Prior systems designed to use social media such as Twitter to predict obesity (a risk factor for T2DM) operate on entire communities such as states, counties, or cities, based on statistics gathered by government agencies. Because there is considerable variation among individuals within these groups, training data on the individual level would be more effective, but this data is difficult to acquire. The approach proposed here aims to address this issue. Our strategy has two steps. First, we trained a random forest classifier on data gathered from (public) Twitter statuses and state-level statistics with state-of-the-art accuracy. We then converted this classifier into a 20-questions-style quiz and made it available online. In doing so, we achieved high engagement with individuals that took the quiz, while also building a training set of voluntarily supplied individual-level data for future classification.
Tasks
Published	2016-03-11
URL	http://arxiv.org/abs/1603.03784v1
PDF	http://arxiv.org/pdf/1603.03784v1.pdf
PWC	https://paperswithcode.com/paper/towards-using-social-media-to-identify
Repo
Framework

Towards Machine Comprehension of Spoken Content: Initial TOEFL Listening Comprehension Test by Machine


Title	Towards Machine Comprehension of Spoken Content: Initial TOEFL Listening Comprehension Test by Machine
Authors	Bo-Hsiang Tseng, Sheng-Syun Shen, Hung-Yi Lee, Lin-Shan Lee
Abstract	Multimedia or spoken content presents more attractive information than plain text content, but it’s more difficult to display on a screen and be selected by a user. As a result, accessing large collections of the former is much more difficult and time-consuming than the latter for humans. It’s highly attractive to develop a machine which can automatically understand spoken content and summarize the key information for humans to browse over. In this endeavor, we propose a new task of machine comprehension of spoken content. We define the initial goal as the listening comprehension test of TOEFL, a challenging academic English examination for English learners whose native language is not English. We further propose an Attention-based Multi-hop Recurrent Neural Network (AMRNN) architecture for this task, achieving encouraging results in the initial tests. Initial results also have shown that word-level attention is probably more robust than sentence-level attention for this task with ASR errors.
Tasks	Reading Comprehension
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06378v1
PDF	http://arxiv.org/pdf/1608.06378v1.pdf
PWC	https://paperswithcode.com/paper/towards-machine-comprehension-of-spoken
Repo
Framework

How to scale distributed deep learning?


Title	How to scale distributed deep learning?
Authors	Peter H. Jin, Qiaochu Yuan, Forrest Iandola, Kurt Keutzer
Abstract	Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification and detection in automatic driver assistance systems (ADAS). To minimize training time, the training of a deep neural network must be scaled beyond a single machine to as many machines as possible by distributing the optimization method used for training. While a number of approaches have been proposed for distributed stochastic gradient descent (SGD), at the current time synchronous approaches to distributed SGD appear to be showing the greatest performance at large scale. Synchronous scaling of SGD suffers from the need to synchronize all processors on each gradient step and is not resilient in the face of failing or lagging processors. In asynchronous approaches using parameter servers, training is slowed by contention to the parameter server. In this paper we compare the convergence of synchronous and asynchronous SGD for training a modern ResNet network architecture on the ImageNet classification problem. We also propose an asynchronous method, gossiping SGD, that aims to retain the positive features of both systems by replacing the all-reduce collective operation of synchronous training with a gossip aggregation algorithm. We find, perhaps counterintuitively, that asynchronous SGD, including both elastic averaging and gossiping, converges faster at fewer nodes (up to about 32 nodes), whereas synchronous SGD scales better to more nodes (up to about 100 nodes).
Tasks	Object Classification
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04581v1
PDF	http://arxiv.org/pdf/1611.04581v1.pdf
PWC	https://paperswithcode.com/paper/how-to-scale-distributed-deep-learning
Repo
Framework

Image Quality Assessment for Performance Evaluation of Focus Measure Operators


Title	Image Quality Assessment for Performance Evaluation of Focus Measure Operators
Authors	Farida Memon, Mukhtiar Ali Unar, Sheeraz Memon
Abstract	This paper presents the performance evaluation of eight focus measure operators namely Image CURV (Curvature), GRAE (Gradient Energy), HISE (Histogram Entropy), LAPM (Modified Laplacian), LAPV (Variance of Laplacian), LAPD (Diagonal Laplacian), LAP3 (Laplacian in 3D Window) and WAVS (Sum of Wavelet Coefficients). Statistical matrics such as MSE (Mean Squared Error), PNSR (Peak Signal to Noise Ratio), SC (Structural Content), NCC (Normalized Cross Correlation), MD (Maximum Difference) and NAE (Normalized Absolute Error) are used to evaluate stated focus measures in this research. . FR (Full Reference) method of the image quality assessment is utilized in this paper. Results indicate that LAPD method is comparatively better than other seven focus operators at typical imaging conditions.
Tasks	Image Quality Assessment
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00546v1
PDF	http://arxiv.org/pdf/1604.00546v1.pdf
PWC	https://paperswithcode.com/paper/image-quality-assessment-for-performance
Repo
Framework

A ParaBoost Stereoscopic Image Quality Assessment (PBSIQA) System


Title	A ParaBoost Stereoscopic Image Quality Assessment (PBSIQA) System
Authors	Hyunsuk Ko, Rui Song, C. -C. Jay Kuo
Abstract	The problem of stereoscopic image quality assessment, which finds applications in 3D visual content delivery such as 3DTV, is investigated in this work. Specifically, we propose a new ParaBoost (parallel-boosting) stereoscopic image quality assessment (PBSIQA) system. The system consists of two stages. In the first stage, various distortions are classified into a few types, and individual quality scorers targeting at a specific distortion type are developed. These scorers offer complementary performance in face of a database consisting of heterogeneous distortion types. In the second stage, scores from multiple quality scorers are fused to achieve the best overall performance, where the fuser is designed based on the parallel boosting idea borrowed from machine learning. Extensive experimental results are conducted to compare the performance of the proposed PBSIQA system with those of existing stereo image quality assessment (SIQA) metrics. The developed quality metric can serve as an objective function to optimize the performance of a 3D content delivery system.
Tasks	Image Quality Assessment
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09469v1
PDF	http://arxiv.org/pdf/1603.09469v1.pdf
PWC	https://paperswithcode.com/paper/a-paraboost-stereoscopic-image-quality
Repo
Framework

Formalizing Neurath’s Ship: Approximate Algorithms for Online Causal Learning


Title	Formalizing Neurath’s Ship: Approximate Algorithms for Online Causal Learning
Authors	Neil R. Bramley, Peter Dayan, Thomas L. Griffiths, David A. Lagnado
Abstract	Higher-level cognition depends on the ability to learn models of the world. We can characterize this at the computational level as a structure-learning problem with the goal of best identifying the prevailing causal relationships among a set of relata. However, the computational cost of performing exact Bayesian inference over causal models grows rapidly as the number of relata increases. This implies that the cognitive processes underlying causal learning must be substantially approximate. A powerful class of approximations that focuses on the sequential absorption of successive inputs is captured by the Neurath’s ship metaphor in philosophy of science, where theory change is cast as a stochastic and gradual process shaped as much by people’s limited willingness to abandon their current theory when considering alternatives as by the ground truth they hope to approach. Inspired by this metaphor and by algorithms for approximating Bayesian inference in machine learning, we propose an algorithmic-level model of causal structure learning under which learners represent only a single global hypothesis that they update locally as they gather evidence. We propose a related scheme for understanding how, under these limitations, learners choose informative interventions that manipulate the causal system to help elucidate its workings. We find support for our approach in the analysis of four experiments.
Tasks	Bayesian Inference
Published	2016-09-14
URL	http://arxiv.org/abs/1609.04212v3
PDF	http://arxiv.org/pdf/1609.04212v3.pdf
PWC	https://paperswithcode.com/paper/formalizing-neuraths-ship-approximate
Repo
Framework

Cross: Efficient Low-rank Tensor Completion


Title	Cross: Efficient Low-rank Tensor Completion
Authors	Anru Zhang
Abstract	The completion of tensors, or high-order arrays, attracts significant attention in recent research. Current literature on tensor completion primarily focuses on recovery from a set of uniformly randomly measured entries, and the required number of measurements to achieve recovery is not guaranteed to be optimal. In addition, the implementation of some previous methods is NP-hard. In this article, we propose a framework for low-rank tensor completion via a novel tensor measurement scheme we name Cross. The proposed procedure is efficient and easy to implement. In particular, we show that a third order tensor of Tucker rank-$(r_1, r_2, r_3)$ in $p_1$-by-$p_2$-by-$p_3$ dimensional space can be recovered from as few as $r_1r_2r_3 + r_1(p_1-r_1) + r_2(p_2-r_2) + r_3(p_3-r_3)$ noiseless measurements, which matches the sample complexity lower-bound. In the case of noisy measurements, we also develop a theoretical upper bound and the matching minimax lower bound for recovery error over certain classes of low-rank tensors for the proposed procedure. The results can be further extended to fourth or higher-order tensors. Simulation studies show that the method performs well under a variety of settings. Finally, the procedure is illustrated through a real dataset in neuroimaging.
Tasks
Published	2016-11-03
URL	http://arxiv.org/abs/1611.01129v2
PDF	http://arxiv.org/pdf/1611.01129v2.pdf
PWC	https://paperswithcode.com/paper/cross-efficient-low-rank-tensor-completion
Repo
Framework

Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)


Title	Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)
Authors	Artem Chernodub, Dimitri Nowicki
Abstract	We propose a novel activation function that implements piece-wise orthogonal non-linear mappings based on permutations. It is straightforward to implement, and very computationally efficient, also it has little memory requirements. We tested it on two toy problems for feedforward and recurrent networks, it shows similar performance to tanh and ReLU. OPLU activation function ensures norm preservance of the backpropagated gradients, therefore it is potentially good for the training of deep, extra deep, and recurrent neural networks.
Tasks
Published	2016-04-08
URL	http://arxiv.org/abs/1604.02313v5
PDF	http://arxiv.org/pdf/1604.02313v5.pdf
PWC	https://paperswithcode.com/paper/norm-preserving-orthogonal-permutation-linear
Repo
Framework

Action-Driven Object Detection with Top-Down Visual Attentions


Title	Action-Driven Object Detection with Top-Down Visual Attentions
Authors	Donggeun Yoo, Sunggyun Park, Kyunghyun Paeng, Joon-Young Lee, In So Kweon
Abstract	A dominant paradigm for deep learning based object detection relies on a “bottom-up” approach using “passive” scoring of class agnostic proposals. These approaches are efficient but lack of holistic analysis of scene-level context. In this paper, we present an “action-driven” detection mechanism using our “top-down” visual attention model. We localize an object by taking sequential actions that the attention model provides. The attention model conditioned with an image region provides required actions to get closer toward a target object. An action at each time step is weak itself but an ensemble of the sequential actions makes a bounding-box accurately converge to a target object boundary. This attention model we call AttentionNet is composed of a convolutional neural network. During our whole detection procedure, we only utilize the actions from a single AttentionNet without any modules for object proposals nor post bounding-box regression. We evaluate our top-down detection mechanism over the PASCAL VOC series and ILSVRC CLS-LOC dataset, and achieve state-of-the-art performances compared to the major bottom-up detection methods. In particular, our detection mechanism shows a strong advantage in elaborate localization by outperforming Faster R-CNN with a margin of +7.1% over PASCAL VOC 2007 when we increase the IoU threshold for positive detection to 0.7.
Tasks	Object Detection
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06704v1
PDF	http://arxiv.org/pdf/1612.06704v1.pdf
PWC	https://paperswithcode.com/paper/action-driven-object-detection-with-top-down
Repo
Framework