May 7, 2019

2777 words 14 mins read

Paper Group ANR 22

Multi-Fold Gabor, PCA and ICA Filter Convolution Descriptor for Face Recognition. Two Discourse Driven Language Models for Semantics. Matrix Product State for Higher-Order Tensor Compression and Classification. X575: writing rengas with web services. Denoising based on wavelets and deblurring via self-organizing map for Synthetic Aperture Radar ima …

Multi-Fold Gabor, PCA and ICA Filter Convolution Descriptor for Face Recognition


Title	Multi-Fold Gabor, PCA and ICA Filter Convolution Descriptor for Face Recognition
Authors	Cheng Yaw Low, Andrew Beng Jin Teoh, Cong Jie Ng
Abstract	This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (M-FFC), for face recognition. On the assumption that M-FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by M-fold to instantiate a filter offspring set. The M-FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters, and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA and ICA filters thus yields three offspring sets: (1) Gabor filters solely, (2) Gabor-PCA filters, and (3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for M-FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into 8 elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.
Tasks	Face Recognition
Published	2016-04-24
URL	http://arxiv.org/abs/1604.07057v3
PDF	http://arxiv.org/pdf/1604.07057v3.pdf
PWC	https://paperswithcode.com/paper/multi-fold-gabor-pca-and-ica-filter
Repo
Framework

Two Discourse Driven Language Models for Semantics


Title	Two Discourse Driven Language Models for Semantics
Authors	Haoruo Peng, Dan Roth
Abstract	Natural language understanding often requires deep semantic knowledge. Expanding on previous proposals, we suggest that some important aspects of semantic knowledge can be modeled as a language model if done at an appropriate level of abstraction. We develop two distinct models that capture semantic frame chains and discourse information while abstracting over the specific mentions of predicates and entities. For each model, we investigate four implementations: a “standard” N-gram language model and three discriminatively trained “neural” language models that generate embeddings for semantic frames. The quality of the semantic language models (SemLM) is evaluated both intrinsically, using perplexity and a narrative cloze test and extrinsically - we show that our SemLM helps improve performance on semantic natural language processing tasks such as co-reference resolution and discourse parsing.
Tasks	Language Modelling
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05679v2
PDF	http://arxiv.org/pdf/1606.05679v2.pdf
PWC	https://paperswithcode.com/paper/two-discourse-driven-language-models-for
Repo
Framework

Matrix Product State for Higher-Order Tensor Compression and Classification


Title	Matrix Product State for Higher-Order Tensor Compression and Classification
Authors	Johann A. Bengua, Ho N. Phien, Hoang D. Tuan, Minh N. Do
Abstract	This paper introduces matrix product state (MPS) decomposition as a new and systematic method to compress multidimensional data represented by higher-order tensors. It solves two major bottlenecks in tensor compression: computation and compression quality. Regardless of tensor order, MPS compresses tensors to matrices of moderate dimension which can be used for classification. Mainly based on a successive sequence of singular value decompositions (SVD), MPS is quite simple to implement and arrives at the global optimal matrix, bypassing local alternating optimization, which is not only computationally expensive but cannot yield the global solution. Benchmark results show that MPS can achieve better classification performance with favorable computation cost compared to other tensor compression methods.
Tasks
Published	2016-09-15
URL	http://arxiv.org/abs/1609.04541v1
PDF	http://arxiv.org/pdf/1609.04541v1.pdf
PWC	https://paperswithcode.com/paper/matrix-product-state-for-higher-order-tensor
Repo
Framework

X575: writing rengas with web services


Title	X575: writing rengas with web services
Authors	Daniel Winterstein, Joseph Corneli
Abstract	Our software system simulates the classical collaborative Japanese poetry form, renga, made of linked haikus. We used NLP methods wrapped up as web services. Our experiments were only a partial success, since results fail to satisfy classical constraints. To gather ideas for future work, we examine related research in semiotics, linguistics, and computing.
Tasks
Published	2016-06-25
URL	http://arxiv.org/abs/1606.07955v1
PDF	http://arxiv.org/pdf/1606.07955v1.pdf
PWC	https://paperswithcode.com/paper/x575-writing-rengas-with-web-services
Repo
Framework

Denoising based on wavelets and deblurring via self-organizing map for Synthetic Aperture Radar images


Title	Denoising based on wavelets and deblurring via self-organizing map for Synthetic Aperture Radar images
Authors	Mario Mastriani
Abstract	This work deals with unsupervised image deblurring. We present a new deblurring procedure on images provided by low-resolution synthetic aperture radar (SAR) or simply by multimedia in presence of multiplicative (speckle) or additive noise, respectively. The method we propose is defined as a two-step process. First, we use an original technique for noise reduction in wavelet domain. Then, the learning of a Kohonen self-organizing map (SOM) is performed directly on the denoised image to take out it the blur. This technique has been successfully applied to real SAR images, and the simulation results are presented to demonstrate the effectiveness of the proposed algorithms.
Tasks	Deblurring, Denoising
Published	2016-07-31
URL	http://arxiv.org/abs/1608.00274v1
PDF	http://arxiv.org/pdf/1608.00274v1.pdf
PWC	https://paperswithcode.com/paper/denoising-based-on-wavelets-and-deblurring
Repo
Framework

Multi-Task Multiple Kernel Relationship Learning


Title	Multi-Task Multiple Kernel Relationship Learning
Authors	Keerthiram Murugesan, Jaime Carbonell
Abstract	This paper presents a novel multitask multiple kernel learning framework that efficiently learns the kernel weights leveraging the relationship across multiple tasks. The idea is to automatically infer this task relationship in the \textit{RKHS} space corresponding to the given base kernels. The problem is formulated as a regularization-based approach called \textit{Multi-Task Multiple Kernel Relationship Learning} (\textit{MK-MTRL}), which models the task relationship matrix from the weights learned from latent feature spaces of task-specific base kernels. Unlike in previous work, the proposed formulation allows one to incorporate prior knowledge for simultaneously learning several related tasks. We propose an alternating minimization algorithm to learn the model parameters, kernel weights and task relationship matrix. In order to tackle large-scale problems, we further propose a two-stage \textit{MK-MTRL} online learning algorithm and show that it significantly reduces the computational time, and also achieves performance comparable to that of the joint learning framework. Experimental results on benchmark datasets show that the proposed formulations outperform several state-of-the-art multitask learning methods.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03427v2
PDF	http://arxiv.org/pdf/1611.03427v2.pdf
PWC	https://paperswithcode.com/paper/multi-task-multiple-kernel-relationship
Repo
Framework

Selective De-noising of Sparse-Coloured Images


Title	Selective De-noising of Sparse-Coloured Images
Authors	Arjun Chaudhuri
Abstract	Since time immemorial, noise has been a constant source of disturbance to the various entities known to mankind. Noise models of different kinds have been developed to study noise in more detailed fashion over the years. Image processing, particularly, has extensively implemented several algorithms to reduce noise in photographs and pictorial documents to alleviate the effect of noise. Images with sparse colours-lesser number of distinct colours in them-are common nowadays, especially in astronomy and astrophysics where black and white colours form the main components. Additive noise of Gaussian type is the most common form of noise to be studied and analysed in majority of communication channels, namely-satellite links, mobile base station to local cellular tower communication channel,et. al. Most of the time, we encounter images from astronomical sources being distorted with noise maximally as they travel long distance from telescopes in outer space to Earth. Considering Additive White Gaussian Noise(AWGN) to be the common noise in these long distance channels, this paper provides an insight and an algorithmic approach to pixel-specific de-noising of sparse-coloured images affected by AWGN. The paper concludes with some essential future avenues and applications of this de-noising method in industry and academia.
Tasks
Published	2016-10-29
URL	http://arxiv.org/abs/1610.09455v1
PDF	http://arxiv.org/pdf/1610.09455v1.pdf
PWC	https://paperswithcode.com/paper/selective-de-noising-of-sparse-coloured
Repo
Framework

Learning the Number of Neurons in Deep Networks


Title	Learning the Number of Neurons in Deep Networks
Authors	Jose M Alvarez, Mathieu Salzmann
Abstract	Nowadays, the number of layers and of neurons in each layer of a deep network are typically set manually. While very deep and wide networks have proven effective in general, they come at a high memory and computation cost, thus making them impractical for constrained platforms. These networks, however, are known to have many redundant parameters, and could thus, in principle, be replaced by more compact architectures. In this paper, we introduce an approach to automatically determining the number of neurons in each layer of a deep network during learning. To this end, we propose to make use of structured sparsity during learning. More precisely, we use a group sparsity regularizer on the parameters of the network, where each group is defined to act on a single neuron. Starting from an overcomplete network, we show that our approach can reduce the number of parameters by up to 80% while retaining or even improving the network accuracy.
Tasks
Published	2016-11-19
URL	http://arxiv.org/abs/1611.06321v3
PDF	http://arxiv.org/pdf/1611.06321v3.pdf
PWC	https://paperswithcode.com/paper/learning-the-number-of-neurons-in-deep
Repo
Framework

Scalable Gaussian Processes for Supervised Hashing


Title	Scalable Gaussian Processes for Supervised Hashing
Authors	Bahadir Ozdemir, Larry S. Davis
Abstract	We propose a flexible procedure for large-scale image search by hash functions with kernels. Our method treats binary codes and pairwise semantic similarity as latent and observed variables, respectively, in a probabilistic model based on Gaussian processes for binary classification. We present an efficient inference algorithm with the sparse pseudo-input Gaussian process (SPGP) model and parallelization. Experiments on three large-scale image dataset demonstrate the effectiveness of the proposed hashing method, Gaussian Process Hashing (GPH), for short binary codes and the datasets without predefined classes in comparison to the state-of-the-art supervised hashing methods.
Tasks	Gaussian Processes, Image Retrieval, Semantic Similarity, Semantic Textual Similarity
Published	2016-04-25
URL	http://arxiv.org/abs/1604.07335v1
PDF	http://arxiv.org/pdf/1604.07335v1.pdf
PWC	https://paperswithcode.com/paper/scalable-gaussian-processes-for-supervised
Repo
Framework

A new analytical approach to consistency and overfitting in regularized empirical risk minimization


Title	A new analytical approach to consistency and overfitting in regularized empirical risk minimization
Authors	Nicolas Garcia Trillos, Ryan Murray
Abstract	This work considers the problem of binary classification: given training data $x_1, \dots, x_n$ from a certain population, together with associated labels $y_1,\dots, y_n \in \left{0,1 \right}$, determine the best label for an element $x$ not among the training data. More specifically, this work considers a variant of the regularized empirical risk functional which is defined intrinsically to the observed data and does not depend on the underlying population. Tools from modern analysis are used to obtain a concise proof of asymptotic consistency as regularization parameters are taken to zero at rates related to the size of the sample. These analytical tools give a new framework for understanding overfitting and underfitting, and rigorously connect the notion of overfitting with a loss of compactness.
Tasks
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00274v1
PDF	http://arxiv.org/pdf/1607.00274v1.pdf
PWC	https://paperswithcode.com/paper/a-new-analytical-approach-to-consistency-and
Repo
Framework

Person Re-identification in Appearance Impaired Scenarios


Title	Person Re-identification in Appearance Impaired Scenarios
Authors	Mengran Gou, Xikang Zhang, Angels Rates-Borras, Sadjad Asghari-Esfeden, Mario Sznaier, Octavia Camps
Abstract	Person re-identification is critical in surveillance applications. Current approaches rely on appearance based features extracted from a single or multiple shots of the target and candidate matches. These approaches are at a disadvantage when trying to distinguish between candidates dressed in similar colors or when targets change their clothing. In this paper we propose a dynamics-based feature to overcome this limitation. The main idea is to capture soft biometrics from gait and motion patterns by gathering dense short trajectories (tracklets) which are Fisher vector encoded. To illustrate the merits of the proposed features we introduce three new “appearance-impaired” datasets. Our experiments on the original and the appearance impaired datasets demonstrate the benefits of incorporating dynamics-based information with appearance-based information to re-identification algorithms.
Tasks	Person Re-Identification
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00367v1
PDF	http://arxiv.org/pdf/1604.00367v1.pdf
PWC	https://paperswithcode.com/paper/person-re-identification-in-appearance
Repo
Framework

Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards


Title	Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards
Authors	Suchet Bargoti, James Underwood
Abstract	Ground vehicles equipped with monocular vision systems are a valuable source of high resolution image data for precision agriculture applications in orchards. This paper presents an image processing framework for fruit detection and counting using orchard image data. A general purpose image segmentation approach is used, including two feature learning algorithms; multi-scale Multi-Layered Perceptrons (MLP) and Convolutional Neural Networks (CNN). These networks were extended by including contextual information about how the image data was captured (metadata), which correlates with some of the appearance variations and/or class distributions observed in the data. The pixel-wise fruit segmentation output is processed using the Watershed Segmentation (WS) and Circular Hough Transform (CHT) algorithms to detect and count individual fruits. Experiments were conducted in a commercial apple orchard near Melbourne, Australia. The results show an improvement in fruit segmentation performance with the inclusion of metadata on the previously benchmarked MLP network. We extend this work with CNNs, bringing agrovision closer to the state-of-the-art in computer vision, where although metadata had negligible influence, the best pixel-wise F1-score of $0.791$ was achieved. The WS algorithm produced the best apple detection and counting results, with a detection F1-score of $0.858$. As a final step, image fruit counts were accumulated over multiple rows at the orchard and compared against the post-harvest fruit counts that were obtained from a grading and counting machine. The count estimates using CNN and WS resulted in the best performance for this dataset, with a squared correlation coefficient of $r^2=0.826$.
Tasks	Semantic Segmentation
Published	2016-10-25
URL	http://arxiv.org/abs/1610.08120v1
PDF	http://arxiv.org/pdf/1610.08120v1.pdf
PWC	https://paperswithcode.com/paper/image-segmentation-for-fruit-detection-and
Repo
Framework

Asymptotic Analysis of Objectives based on Fisher Information in Active Learning


Title	Asymptotic Analysis of Objectives based on Fisher Information in Active Learning
Authors	Jamshid Sourati, Murat Akcakaya, Todd K. Leen, Deniz Erdogmus, Jennifer G. Dy
Abstract	Obtaining labels can be costly and time-consuming. Active learning allows a learning algorithm to intelligently query samples to be labeled for efficient learning. Fisher information ratio (FIR) has been used as an objective for selecting queries in active learning. However, little is known about the theory behind the use of FIR for active learning. There is a gap between the underlying theory and the motivation of its usage in practice. In this paper, we attempt to fill this gap and provide a rigorous framework for analyzing existing FIR-based active learning methods. In particular, we show that FIR can be asymptotically viewed as an upper bound of the expected variance of the log-likelihood ratio. Additionally, our analysis suggests a unifying framework that not only enables us to make theoretical comparisons among the existing querying methods based on FIR, but also allows us to give insight into the development of new active learning approaches based on this objective.
Tasks	Active Learning
Published	2016-05-27
URL	http://arxiv.org/abs/1605.08798v2
PDF	http://arxiv.org/pdf/1605.08798v2.pdf
PWC	https://paperswithcode.com/paper/asymptotic-analysis-of-objectives-based-on
Repo
Framework

Deep Restricted Boltzmann Networks


Title	Deep Restricted Boltzmann Networks
Authors	Hengyuan Hu, Lisheng Gao, Quanbin Ma
Abstract	Building a good generative model for image has long been an important topic in computer vision and machine learning. Restricted Boltzmann machine (RBM) is one of such models that is simple but powerful. However, its restricted form also has placed heavy constraints on the models representation power and scalability. Many extensions have been invented based on RBM in order to produce deeper architectures with greater power. The most famous ones among them are deep belief network, which stacks multiple layer-wise pretrained RBMs to form a hybrid model, and deep Boltzmann machine, which allows connections between hidden units to form a multi-layer structure. In this paper, we present a new method to compose RBMs to form a multi-layer network style architecture and a training method that trains all layers jointly. We call the resulted structure deep restricted Boltzmann network. We further explore the combination of convolutional RBM with the normal fully connected RBM, which is made trivial under our composition framework. Experiments show that our model can generate descent images and outperform the normal RBM significantly in terms of image quality and feature quality, without losing much efficiency for training.
Tasks
Published	2016-11-15
URL	http://arxiv.org/abs/1611.07917v1
PDF	http://arxiv.org/pdf/1611.07917v1.pdf
PWC	https://paperswithcode.com/paper/deep-restricted-boltzmann-networks
Repo
Framework

A Comparative Study of Object Trackers for Infrared Flying Bird Tracking


Title	A Comparative Study of Object Trackers for Infrared Flying Bird Tracking
Authors	Ying Huang, Hong Zheng, Haibin Ling, Erik Blasch, Hao Yang
Abstract	Bird strikes present a huge risk for aircraft, especially since traditional airport bird surveillance is mainly dependent on inefficient human observation. Computer vision based technology has been proposed to automatically detect birds, determine bird flying trajectories, and predict aircraft takeoff delays. However, the characteristics of bird flight using imagery and the performance of existing methods applied to flying bird task are not well known. Therefore, we perform infrared flying bird tracking experiments using 12 state-of-the-art algorithms on a real BIRDSITE-IR dataset to obtain useful clues and recommend feature analysis. We also develop a Struck-scale method to demonstrate the effectiveness of multiple scale sampling adaption in handling the object of flying bird with varying shape and scale. The general analysis can be used to develop specialized bird tracking methods for airport safety, wildness and urban bird population studies.
Tasks
Published	2016-01-18
URL	http://arxiv.org/abs/1601.04386v1
PDF	http://arxiv.org/pdf/1601.04386v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-of-object-trackers-for
Repo
Framework