July 27, 2019

2763 words 13 mins read

Paper Group ANR 721

Nonparametric Online Regression while Learning the Metric. The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis. Compressive Sensing Approaches for Autonomous Object Detection in Video Sequences. Fast, Accurate and Fully Parallelizable Digital Image Correlation. Image Segmentatio …

Nonparametric Online Regression while Learning the Metric


Title	Nonparametric Online Regression while Learning the Metric
Authors	Ilja Kuzborskij, Nicolò Cesa-Bianchi
Abstract	We study algorithms for online nonparametric regression that learn the directions along which the regression function is smoother. Our algorithm learns the Mahalanobis metric based on the gradient outer product matrix $\boldsymbol{G}$ of the regression function (automatically adapting to the effective rank of this matrix), while simultaneously bounding the regret —on the same data sequence— in terms of the spectrum of $\boldsymbol{G}$. As a preliminary step in our analysis, we extend a nonparametric online learning algorithm by Hazan and Megiddo enabling it to compete against functions whose Lipschitzness is measured with respect to an arbitrary Mahalanobis metric.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07853v2
PDF	http://arxiv.org/pdf/1705.07853v2.pdf
PWC	https://paperswithcode.com/paper/nonparametric-online-regression-while
Repo
Framework

The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis


Title	The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis
Authors	Audrey Chung, Mohammad Javad Shafiee, Paul Fieguth, Alexander Wong
Abstract	Evolutionary deep intelligence was recently proposed as a method for achieving highly efficient deep neural network architectures over successive generations. Drawing inspiration from nature, we propose the incorporation of sexual evolutionary synthesis. Rather than the current asexual synthesis of networks, we aim to produce more compact feature representations by synthesizing more diverse and generalizable offspring networks in subsequent generations via the combination of two parent networks. Experimental results were obtained using the MNIST and CIFAR-10 datasets, and showed improved architectural efficiency and comparable testing accuracy relative to the baseline asexual evolutionary neural networks. In particular, the network synthesized via sexual evolutionary synthesis for MNIST had approximately double the architectural efficiency (cluster efficiency of 34.29X and synaptic efficiency of 258.37X) in comparison to the network synthesized via asexual evolutionary synthesis, with both networks achieving a testing accuracy of ~97%.
Tasks
Published	2017-09-07
URL	http://arxiv.org/abs/1709.02043v1
PDF	http://arxiv.org/pdf/1709.02043v1.pdf
PWC	https://paperswithcode.com/paper/the-mating-rituals-of-deep-neural-networks
Repo
Framework

Compressive Sensing Approaches for Autonomous Object Detection in Video Sequences


Title	Compressive Sensing Approaches for Autonomous Object Detection in Video Sequences
Authors	Danil Kuzin, Olga Isupova, Lyudmila Mihaylova
Abstract	Video analytics requires operating with large amounts of data. Compressive sensing allows to reduce the number of measurements required to represent the video using the prior knowledge of sparsity of the original signal, but it imposes certain conditions on the design matrix. The Bayesian compressive sensing approach relaxes the limitations of the conventional approach using the probabilistic reasoning and allows to include different prior knowledge about the signal structure. This paper presents two Bayesian compressive sensing methods for autonomous object detection in a video sequence from a static camera. Their performance is compared on the real datasets with the non-Bayesian greedy algorithm. It is shown that the Bayesian methods can provide the same accuracy as the greedy algorithm but much faster; or if the computational time is not critical they can provide more accurate results.
Tasks	Compressive Sensing, Object Detection
Published	2017-04-27
URL	http://arxiv.org/abs/1705.00002v1
PDF	http://arxiv.org/pdf/1705.00002v1.pdf
PWC	https://paperswithcode.com/paper/compressive-sensing-approaches-for-autonomous
Repo
Framework

Fast, Accurate and Fully Parallelizable Digital Image Correlation


Title	Fast, Accurate and Fully Parallelizable Digital Image Correlation
Authors	Peihan Tu
Abstract	Digital image correlation (DIC) is a widely used optical metrology for surface deformation measurements. DIC relies on nonlinear optimization method. Thus an initial guess is quite important due to its influence on the converge characteristics of the algorithm. In order to obtain a reliable, accurate initial guess, a reliability-guided digital image correlation (RG-DIC) method, which is able to intelligently obtain a reliable initial guess without using time-consuming integer-pixel registration, was proposed. However, the RG-DIC and its improved methods are path-dependent and cannot be fully parallelized. Besides, it is highly possible that RG-DIC fails in the full-field analysis of deformation without manual intervention if the deformation fields contain large areas of discontinuous deformation. Feature-based initial guess is highly robust while it is relatively time-consuming. Recently, path-independent algorithm, fast Fourier transform-based cross correlation (FFT-CC) algorithm, was proposed to estimate the initial guess. Complete parallelizability is the major advantage of the FFT-CC algorithm, while it is sensitive to small deformation. Wu et al proposed an efficient integer-pixel search scheme, but the parameters of this algorithm are set by the users empirically. In this technical note, a fully parallelizable DIC method is proposed. Different from RG-DIC method, the proposed method divides DIC algorithm into two parts: full-field initial guess estimation and sub-pixel registration. The proposed method has the following benefits: 1) providing a pre-knowledge of deformation fields; 2) saving computational time; 3) reducing error propagation; 4) integratability with well-established DIC algorithms; 5) fully parallelizability.
Tasks
Published	2017-10-12
URL	https://arxiv.org/abs/1710.04374v2
PDF	https://arxiv.org/pdf/1710.04374v2.pdf
PWC	https://paperswithcode.com/paper/fast-accurate-and-fully-parallelizable
Repo
Framework

Image Segmentation by Iterative Inference from Conditional Score Estimation


Title	Image Segmentation by Iterative Inference from Conditional Score Estimation
Authors	Adriana Romero, Michal Drozdzal, Akram Erraqabi, Simon Jégou, Yoshua Bengio
Abstract	Inspired by the combination of feedforward and iterative computations in the virtual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of a joint distribution, we propose a novel approach to iterative inference for capturing and exploiting the complex joint distribution of output variables conditioned on some input variables. This approach is applied to image pixel-wise segmentation, with the estimated conditional score used to perform gradient ascent towards a mode of the estimated conditional distribution. This extends previous work on score estimation by denoising autoencoders to the case of a conditional distribution, with a novel use of a corrupted feedforward predictor replacing Gaussian corruption. An advantage of this approach over more classical ways to perform iterative inference for structured outputs, like conditional random fields (CRFs), is that it is not any more necessary to define an explicit energy function linking the output variables. To keep computations tractable, such energy function parametrizations are typically fairly constrained, involving only a few neighbors of each of the output variables in each clique. We experimentally find that the proposed iterative inference from conditional score estimation by conditional denoising autoencoders performs better than comparable models based on CRFs or those not using any explicit modeling of the conditional joint distribution of outputs.
Tasks	Denoising, Semantic Segmentation
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07450v2
PDF	http://arxiv.org/pdf/1705.07450v2.pdf
PWC	https://paperswithcode.com/paper/image-segmentation-by-iterative-inference
Repo
Framework

Learning Sparse Adversarial Dictionaries For Multi-Class Audio Classification


Title	Learning Sparse Adversarial Dictionaries For Multi-Class Audio Classification
Authors	Vaisakh Shaj, Puranjoy Bhattacharya
Abstract	Audio events are quite often overlapping in nature, and more prone to noise than visual signals. There has been increasing evidence for the superior performance of representations learned using sparse dictionaries for applications like audio denoising and speech enhancement. This paper concentrates on modifying the traditional reconstructive dictionary learning algorithms, by incorporating a discriminative term into the objective function in order to learn class-specific adversarial dictionaries that are good at representing samples of their own class at the same time poor at representing samples belonging to any other class. We quantitatively demonstrate the effectiveness of our learned dictionaries as a stand-alone solution for both binary as well as multi-class audio classification problems.
Tasks	Audio Classification, Audio Denoising, Denoising, Dictionary Learning, Speech Enhancement
Published	2017-12-02
URL	http://arxiv.org/abs/1712.00640v1
PDF	http://arxiv.org/pdf/1712.00640v1.pdf
PWC	https://paperswithcode.com/paper/learning-sparse-adversarial-dictionaries-for
Repo
Framework

Privacy Preserving Face Retrieval in the Cloud for Mobile Users


Title	Privacy Preserving Face Retrieval in the Cloud for Mobile Users
Authors	Xin Jin, Shiming Ge, Chenggen Song
Abstract	Recently, cloud storage and processing have been widely adopted. Mobile users in one family or one team may automatically backup their photos to the same shared cloud storage space. The powerful face detector trained and provided by a 3rd party may be used to retrieve the photo collection which contains a specific group of persons from the cloud storage server. However, the privacy of the mobile users may be leaked to the cloud server providers. In the meanwhile, the copyright of the face detector should be protected. Thus, in this paper, we propose a protocol of privacy preserving face retrieval in the cloud for mobile users, which protects the user photos and the face detector simultaneously. The cloud server only provides the resources of storage and computing and can not learn anything of the user photos and the face detector. We test our protocol inside several families and classes. The experimental results reveal that our protocol can successfully retrieve the proper photos from the cloud server and protect the user photos and the face detector.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02872v1
PDF	http://arxiv.org/pdf/1708.02872v1.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-face-retrieval-in-the
Repo
Framework

Helping AI to Play Hearthstone: AAIA’17 Data Mining Challenge


Title	Helping AI to Play Hearthstone: AAIA’17 Data Mining Challenge
Authors	Andrzej Janusz, Maciej Świechowski, Tomasz Tajmajer
Abstract	This paper summarizes the AAIA’17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform. We briefly describe the scope and background of this competition in the context of a more general project related to the development of an AI engine for video games, called Grail. We also discuss the outcomes of this challenge and demonstrate how predictive models for the assessment of player’s winning chances can be utilized in a construction of an intelligent agent for playing Hearthstone. Finally, we show a few selected machine learning approaches for modeling state and action values in Hearthstone. We provide evaluation for a few promising solutions that may be used to create more advanced types of agents, especially in conjunction with Monte Carlo Tree Search algorithms.
Tasks
Published	2017-08-02
URL	http://arxiv.org/abs/1708.00730v1
PDF	http://arxiv.org/pdf/1708.00730v1.pdf
PWC	https://paperswithcode.com/paper/helping-ai-to-play-hearthstone-aaia17-data
Repo
Framework

Hot-Rodding the Browser Engine: Automatic Configuration of JavaScript Compilers


Title	Hot-Rodding the Browser Engine: Automatic Configuration of JavaScript Compilers
Authors	Chris Fawcett, Lars Kotthoff, Holger H. Hoos
Abstract	Modern software systems in many application areas offer to the user a multitude of parameters, switches and other customisation hooks. Humans tend to have difficulties determining the best configurations for particular applications. Modern optimising compilers are an example of such software systems; their many parameters need to be tuned for optimal performance, but are often left at the default values for convenience. In this work, we automatically determine compiler parameter settings that result in optimised performance for particular applications. Specifically, we apply a state-of-the-art automated parameter configuration procedure based on cutting-edge machine learning and optimisation techniques to two prominent JavaScript compilers and demonstrate that significant performance improvements, more than 35% in some cases, can be achieved over the default parameter settings on a diverse set of benchmarks.
Tasks
Published	2017-07-11
URL	http://arxiv.org/abs/1707.04245v1
PDF	http://arxiv.org/pdf/1707.04245v1.pdf
PWC	https://paperswithcode.com/paper/hot-rodding-the-browser-engine-automatic
Repo
Framework

A GAMP Based Low Complexity Sparse Bayesian Learning Algorithm


Title	A GAMP Based Low Complexity Sparse Bayesian Learning Algorithm
Authors	Maher Al-Shoukairi, Philip Schniter, Bhaskar D. Rao
Abstract	In this paper, we present an algorithm for the sparse signal recovery problem that incorporates damped Gaussian generalized approximate message passing (GGAMP) into Expectation-Maximization (EM)-based sparse Bayesian learning (SBL). In particular, GGAMP is used to implement the E-step in SBL in place of matrix inversion, leveraging the fact that GGAMP is guaranteed to converge with appropriate damping. The resulting GGAMP-SBL algorithm is much more robust to arbitrary measurement matrix $\boldsymbol{A}$ than the standard damped GAMP algorithm while being much lower complexity than the standard SBL algorithm. We then extend the approach from the single measurement vector (SMV) case to the temporally correlated multiple measurement vector (MMV) case, leading to the GGAMP-TSBL algorithm. We verify the robustness and computational advantages of the proposed algorithms through numerical experiments.
Tasks
Published	2017-03-08
URL	http://arxiv.org/abs/1703.03044v2
PDF	http://arxiv.org/pdf/1703.03044v2.pdf
PWC	https://paperswithcode.com/paper/a-gamp-based-low-complexity-sparse-bayesian
Repo
Framework

Understanding People Flow in Transportation Hubs


Title	Understanding People Flow in Transportation Hubs
Authors	João Carvalho, Manuel Marques, João P. Costeira
Abstract	In this paper, we aim to monitor the flow of people in large public infrastructures. We propose an unsupervised methodology to cluster people flow patterns into the most typical and meaningful configurations. By processing 3D images from a network of depth cameras, we build a descriptor for the flow pattern. We define a data-irregularity measure that assesses how well each descriptor fits a data model. This allows us to rank flow patterns from highly distinctive (outliers) to very common ones. By discarding outliers, we obtain more reliable key configurations (classes). Synthetic experiments show that the proposed method is superior to standard clustering methods. We applied it in an operational scenario during 14 days in the X-ray screening area of an international airport. Results show that our methodology is able to successfully summarize the representative patterns for such a long observation period, providing relevant information for airport management. Beyond regular flows, our method identifies a set of rare events corresponding to uncommon activities (cleaning, special security and circulating staff).
Tasks
Published	2017-04-28
URL	http://arxiv.org/abs/1705.00027v2
PDF	http://arxiv.org/pdf/1705.00027v2.pdf
PWC	https://paperswithcode.com/paper/understanding-people-flow-in-transportation
Repo
Framework

Addressing Ambiguity in Multi-target Tracking by Hierarchical Strategy


Title	Addressing Ambiguity in Multi-target Tracking by Hierarchical Strategy
Authors	Ali Taalimi, Liu Liu, Hairong Qi
Abstract	This paper presents a novel hierarchical approach for the simultaneous tracking of multiple targets in a video. We use a network flow approach to link detections in low-level and tracklets in high-level. At each step of the hierarchy, the confidence of candidates is measured by using a new scoring system, ConfRank, that considers the quality and the quantity of its neighborhood. The output of the first stage is a collection of safe tracklets and unlinked high-confidence detections. For each individual detection, we determine if it belongs to an existing or is a new tracklet. We show the effect of our framework to recover missed detections and reduce switch identity. The proposed tracker is referred to as TVOD for multi-target tracking using the visual tracker and generic object detector. We achieve competitive results with lower identity switches on several datasets comparing to state-of-the-art.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10716v1
PDF	http://arxiv.org/pdf/1705.10716v1.pdf
PWC	https://paperswithcode.com/paper/addressing-ambiguity-in-multi-target-tracking
Repo
Framework

Experience enrichment based task independent reward model


Title	Experience enrichment based task independent reward model
Authors	Min Xu
Abstract	For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex interactions between agents and environments. In this paper, we propose an implicit generic reward model for reinforcement learning. Unlike those rewards that are manually defined for specific tasks, such implicit reward is task independent. It only comes from the deviation from the agents’ previous experiences.
Tasks
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07460v1
PDF	http://arxiv.org/pdf/1705.07460v1.pdf
PWC	https://paperswithcode.com/paper/experience-enrichment-based-task-independent
Repo
Framework

Single Image Super-Resolution based on Wiener Filter in Similarity Domain


Title	Single Image Super-Resolution based on Wiener Filter in Similarity Domain
Authors	Cristóvão Cruz, Rakesh Mehta, Vladimir Katkovnik, Karen Egiazarian
Abstract	Single image super resolution (SISR) is an ill-posed problem aiming at estimating a plausible high resolution (HR) image from a single low resolution (LR) image. Current state-of-the-art SISR methods are patch-based. They use either external data or internal self-similarity to learn a prior for a HR image. External data based methods utilize large number of patches from the training data, while self-similarity based approaches leverage one or more similar patches from the input image. In this paper we propose a self-similarity based approach that is able to use large groups of similar patches extracted from the input image to solve the SISR problem. We introduce a novel prior leading to collaborative filtering of patch groups in 1D similarity domain and couple it with an iterative back-projection framework. The performance of the proposed algorithm is evaluated on a number of SISR benchmark datasets. Without using any external data, the proposed approach outperforms the current non-CNN based methods on the tested datasets for various scaling factors. On certain datasets, the gain is over 1 dB, when compared to the recent method A+. For high sampling rate (x4) the proposed method performs similarly to very recent state-of-the-art deep convolutional network based approaches.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04126v3
PDF	http://arxiv.org/pdf/1704.04126v3.pdf
PWC	https://paperswithcode.com/paper/single-image-super-resolution-based-on-wiener
Repo
Framework

Deep Learning Methods for Efficient Large Scale Video Labeling


Title	Deep Learning Methods for Efficient Large Scale Video Labeling
Authors	Miha Skalic, Marcin Pekalski, Xingguo E. Pan
Abstract	We present a solution to “Google Cloud and YouTube-8M Video Understanding Challenge” that ranked 5th place. The proposed model is an ensemble of three model families, two frame level and one video level. The training was performed on augmented dataset, with cross validation.
Tasks	Video Understanding
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04572v1
PDF	http://arxiv.org/pdf/1706.04572v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-methods-for-efficient-large
Repo
Framework