May 5, 2019

3117 words 15 mins read

Paper Group ANR 497

Bayesian Modeling of Motion Perception using Dynamical Stochastic Textures. Monocular Urban Localization using Street View. Patch-based Texture Synthesis for Image Inpainting. Efficient Parallel Learning of Word2Vec. Robust Contextual Outlier Detection: Where Context Meets Sparsity. Efficient Splitting-based Method for Global Image Smoothing. A Fea …

Bayesian Modeling of Motion Perception using Dynamical Stochastic Textures


Title	Bayesian Modeling of Motion Perception using Dynamical Stochastic Textures
Authors	Jonathan Vacher, Andrew Isaac Meso, Laurent U. Perrinet, Gabriel Peyré
Abstract	A common practice to account for psychophysical biases in vision is to frame them as consequences of a dynamic process relying on optimal inference with respect to a generative model. The present study details the complete formulation of such a generative model intended to probe visual motion perception with a dynamic texture model. It is first derived in a set of axiomatic steps constrained by biological plausibility. We extend previous contributions by detailing three equivalent formulations of this texture model. First, the composite dynamic textures are constructed by the random aggregation of warped patterns, which can be viewed as 3D Gaussian fields. Secondly, these textures are cast as solutions to a stochastic partial differential equation (sPDE). This essential step enables real time, on-the-fly texture synthesis using time-discretized auto-regressive processes. It also allows for the derivation of a local motion-energy model, which corresponds to the log-likelihood of the probability density. The log-likelihoods are essential for the construction of a Bayesian inference framework. We use the dynamic texture model to psychophysically probe speed perception in humans using zoom-like changes in the spatial frequency content of the stimulus. The human data replicates previous findings showing perceived speed to be positively biased by spatial frequency increments. A Bayesian observer who combines a Gaussian likelihood centered at the true speed and a spatial frequency dependent width with a “slow speed prior” successfully accounts for the perceptual bias. More precisely, the bias arises from a decrease in the observer’s likelihood width estimated from the experiments as the spatial frequency increases. Such a trend is compatible with the trend of the dynamic texture likelihood width.
Tasks	Bayesian Inference, Texture Synthesis
Published	2016-11-02
URL	http://arxiv.org/abs/1611.01390v2
PDF	http://arxiv.org/pdf/1611.01390v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-modeling-of-motion-perception-using
Repo
Framework

Monocular Urban Localization using Street View


Title	Monocular Urban Localization using Street View
Authors	Li Yu, Cyril Joly, Guillaume Bresson, Fabien Moutarde
Abstract	This paper presents a metric global localization in the urban environment only with a monocular camera and the Google Street View database. We fully leverage the abundant sources from the Street View and benefits from its topo-metric structure to build a coarse-to-fine positioning, namely a topological place recognition process and then a metric pose estimation by local bundle adjustment. Our method is tested on a 3 km urban environment and demonstrates both sub-meter accuracy and robustness to viewpoint changes, illumination and occlusion. To our knowledge, this is the first work that studies the global urban localization simply with a single camera and Street View.
Tasks	Pose Estimation
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05157v2
PDF	http://arxiv.org/pdf/1605.05157v2.pdf
PWC	https://paperswithcode.com/paper/monocular-urban-localization-using-street
Repo
Framework

Patch-based Texture Synthesis for Image Inpainting


Title	Patch-based Texture Synthesis for Image Inpainting
Authors	Tao Zhou, Brian Johnson, Rui Li
Abstract	Image inpaiting is an important task in image processing and vision. In this paper, we develop a general method for patch-based image inpainting by synthesizing new textures from existing one. A novel framework is introduced to find several optimal candidate patches and generate a new texture patch in the process. We form it as an optimization problem that identifies the potential patches for synthesis from an coarse-to-fine manner. We use the texture descriptor as a clue in searching for matching patches from the known region. To ensure the structure faithful to the original image, a geometric constraint metric is formally defined that is applied directly to the patch synthesis procedure. We extensively conducted our experiments on a wide range of testing images on various scenarios and contents by arbitrarily specifying the target the regions for inference followed by using existing evaluation metrics to verify its texture coherency and structural consistency. Our results demonstrate the high accuracy and desirable output that can be potentially used for numerous applications: object removal, background subtraction, and image retrieval.
Tasks	Image Inpainting, Image Retrieval, Texture Synthesis
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01576v1
PDF	http://arxiv.org/pdf/1605.01576v1.pdf
PWC	https://paperswithcode.com/paper/patch-based-texture-synthesis-for-image
Repo
Framework

Efficient Parallel Learning of Word2Vec


Title	Efficient Parallel Learning of Word2Vec
Authors	Jeroen B. P. Vuurens, Carsten Eickhoff, Arjen P. de Vries
Abstract	Since its introduction, Word2Vec and its variants are widely used to learn semantics-preserving representations of words or entities in an embedding space, which can be used to produce state-of-art results for various Natural Language Processing tasks. Existing implementations aim to learn efficiently by running multiple threads in parallel while operating on a single model in shared memory, ignoring incidental memory update collisions. We show that these collisions can degrade the efficiency of parallel learning, and propose a straightforward caching strategy that improves the efficiency by a factor of 4.
Tasks
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07822v1
PDF	http://arxiv.org/pdf/1606.07822v1.pdf
PWC	https://paperswithcode.com/paper/efficient-parallel-learning-of-word2vec
Repo
Framework

Robust Contextual Outlier Detection: Where Context Meets Sparsity


Title	Robust Contextual Outlier Detection: Where Context Meets Sparsity
Authors	Jiongqian Liang, Srinivasan Parthasarathy
Abstract	Outlier detection is a fundamental data science task with applications ranging from data cleaning to network security. Given the fundamental nature of the task, this has been the subject of much research. Recently, a new class of outlier detection algorithms has emerged, called {\it contextual outlier detection}, and has shown improved performance when studying anomalous behavior in a specific context. However, as we point out in this article, such approaches have limited applicability in situations where the context is sparse (i.e. lacking a suitable frame of reference). Moreover, approaches developed to date do not scale to large datasets. To address these problems, here we propose a novel and robust approach alternative to the state-of-the-art called RObust Contextual Outlier Detection (ROCOD). We utilize a local and global behavioral model based on the relevant contexts, which is then integrated in a natural and robust fashion. We also present several optimizations to improve the scalability of the approach. We run ROCOD on both synthetic and real-world datasets and demonstrate that it outperforms other competitive baselines on the axes of efficacy and efficiency (40X speedup compared to modern contextual outlier detection methods). We also drill down and perform a fine-grained analysis to shed light on the rationale for the performance gains of ROCOD and reveal its effectiveness when handling objects with sparse contexts.
Tasks	Outlier Detection
Published	2016-07-28
URL	http://arxiv.org/abs/1607.08329v3
PDF	http://arxiv.org/pdf/1607.08329v3.pdf
PWC	https://paperswithcode.com/paper/robust-contextual-outlier-detection-where
Repo
Framework

Efficient Splitting-based Method for Global Image Smoothing


Title	Efficient Splitting-based Method for Global Image Smoothing
Authors	Youngjung Kim, Dongbo Min, Bumsub Ham, Kwanghoon Sohn
Abstract	Edge-preserving smoothing (EPS) can be formulated as minimizing an objective function that consists of data and prior terms. This global EPS approach shows better smoothing performance than a local one that typically has a form of weighted averaging, at the price of high computational cost. In this paper, we introduce a highly efficient splitting-based method for global EPS that minimizes the objective function of ${l_2}$ data and prior terms (possibly non-smooth and non-convex) in linear time. Different from previous splitting-based methods that require solving a large linear system, our approach solves an equivalent constrained optimization problem, resulting in a sequence of 1D sub-problems. This enables linear time solvers for weighted-least squares and -total variation problems. Our solver converges quickly, and its runtime is even comparable to state-of-the-art local EPS approaches. We also propose a family of fast iteratively re-weighted algorithms using a non-convex prior term. Experimental results demonstrate the effectiveness and flexibility of our approach in a range of computer vision and image processing tasks.
Tasks
Published	2016-04-26
URL	http://arxiv.org/abs/1604.07681v1
PDF	http://arxiv.org/pdf/1604.07681v1.pdf
PWC	https://paperswithcode.com/paper/efficient-splitting-based-method-for-global
Repo
Framework

A Feature Learning and Object Recognition Framework for Underwater Fish Images


Title	A Feature Learning and Object Recognition Framework for Underwater Fish Images
Authors	Meng-Che Chuang, Jenq-Neng Hwang, Kresimir Williams
Abstract	Live fish recognition is one of the most crucial elements of fisheries survey applications where vast amount of data are rapidly acquired. Different from general scenarios, challenges to underwater image recognition are posted by poor image quality, uncontrolled objects and environment, as well as difficulty in acquiring representative samples. Also, most existing feature extraction techniques are hindered from automation due to involving human supervision. Toward this end, we propose an underwater fish recognition framework that consists of a fully unsupervised feature learning technique and an error-resilient classifier. Object parts are initialized based on saliency and relaxation labeling to match object parts correctly. A non-rigid part model is then learned based on fitness, separation and discrimination criteria. For the classifier, an unsupervised clustering approach generates a binary class hierarchy, where each node is a classifier. To exploit information from ambiguous images, the notion of partial classification is introduced to assign coarse labels by optimizing the “benefit” of indecision made by the classifier. Experiments show that the proposed framework achieves high accuracy on both public and self-collected underwater fish images with high uncertainty and class imbalance.
Tasks	Object Recognition
Published	2016-03-05
URL	http://arxiv.org/abs/1603.01696v1
PDF	http://arxiv.org/pdf/1603.01696v1.pdf
PWC	https://paperswithcode.com/paper/a-feature-learning-and-object-recognition
Repo
Framework

Crowdsourcing scoring of immunohistochemistry images: Evaluating Performance of the Crowd and an Automated Computational Method


Title	Crowdsourcing scoring of immunohistochemistry images: Evaluating Performance of the Crowd and an Automated Computational Method
Authors	Humayun Irshad, Eun-Yeong Oh, Daniel Schmolze, Liza M Quintana, Laura Collins, Rulla M. Tamimi, Andrew H. Beck
Abstract	The assessment of protein expression in immunohistochemistry (IHC) images provides important diagnostic, prognostic and predictive information for guiding cancer diagnosis and therapy. Manual scoring of IHC images represents a logistical challenge, as the process is labor intensive and time consuming. Since the last decade, computational methods have been developed to enable the application of quantitative methods for the analysis and interpretation of protein expression in IHC images. These methods have not yet replaced manual scoring for the assessment of IHC in the majority of diagnostic laboratories and in many large-scale research studies. An alternative approach is crowdsourcing the quantification of IHC images to an undefined crowd. The aim of this study is to quantify IHC images for labeling of ER status with two different crowdsourcing approaches, image labeling and nuclei labeling, and compare their performance with automated methods. Crowdsourcing-derived scores obtained greater concordance with the pathologist interpretations for both image labeling and nuclei labeling tasks (83% and 87%), as compared to the pathologist concordance achieved by the automated method (81%) on 5,483 TMA images from 1,909 breast cancer patients. This analysis shows that crowdsourcing the scoring of protein expression in IHC images is a promising new approach for large scale cancer molecular pathology studies.
Tasks
Published	2016-06-21
URL	http://arxiv.org/abs/1606.06681v2
PDF	http://arxiv.org/pdf/1606.06681v2.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-scoring-of-immunohistochemistry
Repo
Framework

Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization


Title	Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization
Authors	Akanksha, Jacob Eisenstein
Abstract	This paper describes the Georgia Tech team’s approach to the CoNLL-2016 supplementary evaluation on discourse relation sense classification. We use long short-term memories (LSTM) to induce distributed representations of each argument, and then combine these representations with surface features in a neural network. The architecture of the neural network is determined by Bayesian hyperparameter search.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04503v1
PDF	http://arxiv.org/pdf/1606.04503v1.pdf
PWC	https://paperswithcode.com/paper/shallow-discourse-parsing-using-distributed
Repo
Framework

Dynamic matrix recovery from incomplete observations under an exact low-rank constraint


Title	Dynamic matrix recovery from incomplete observations under an exact low-rank constraint
Authors	Liangbei Xu, Mark A. Davenport
Abstract	Low-rank matrix factorizations arise in a wide variety of applications – including recommendation systems, topic models, and source separation, to name just a few. In these and many other applications, it has been widely noted that by incorporating temporal information and allowing for the possibility of time-varying models, significant improvements are possible in practice. However, despite the reported superior empirical performance of these dynamic models over their static counterparts, there is limited theoretical justification for introducing these more complex models. In this paper we aim to address this gap by studying the problem of recovering a dynamically evolving low-rank matrix from incomplete observations. First, we propose the locally weighted matrix smoothing (LOWEMS) framework as one possible approach to dynamic matrix recovery. We then establish error bounds for LOWEMS in both the {\em matrix sensing} and {\em matrix completion} observation models. Our results quantify the potential benefits of exploiting dynamic constraints both in terms of recovery accuracy and sample complexity. To illustrate these benefits we provide both synthetic and real-world experimental results.
Tasks	Matrix Completion, Recommendation Systems, Topic Models
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09420v1
PDF	http://arxiv.org/pdf/1610.09420v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-matrix-recovery-from-incomplete
Repo
Framework

The Artificial Mind’s Eye: Resisting Adversarials for Convolutional Neural Networks using Internal Projection


Title	The Artificial Mind’s Eye: Resisting Adversarials for Convolutional Neural Networks using Internal Projection
Authors	Harm Berntsen, Wouter Kuijper, Tom Heskes
Abstract	We introduce a novel artificial neural network architecture that integrates robustness to adversarial input in the network structure. The main idea of our approach is to force the network to make predictions on what the given instance of the class under consideration would look like and subsequently test those predictions. By forcing the network to redraw the relevant parts of the image and subsequently comparing this new image to the original, we are having the network give a “proof” of the presence of the object.
Tasks
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04428v2
PDF	http://arxiv.org/pdf/1604.04428v2.pdf
PWC	https://paperswithcode.com/paper/the-artificial-minds-eye-resisting
Repo
Framework

A Framework for Searching for General Artificial Intelligence


Title	A Framework for Searching for General Artificial Intelligence
Authors	Marek Rosa, Jan Feyereisl, The GoodAI Collective
Abstract	There is a significant lack of unified approaches to building generally intelligent machines. The majority of current artificial intelligence research operates within a very narrow field of focus, frequently without considering the importance of the ‘big picture’. In this document, we seek to describe and unify principles that guide the basis of our development of general artificial intelligence. These principles revolve around the idea that intelligence is a tool for searching for general solutions to problems. We define intelligence as the ability to acquire skills that narrow this search, diversify it and help steer it to more promising areas. We also provide suggestions for studying, measuring, and testing the various skills and abilities that a human-level intelligent machine needs to acquire. The document aims to be both implementation agnostic, and to provide an analytic, systematic, and scalable way to generate hypotheses that we believe are needed to meet the necessary conditions in the search for general artificial intelligence. We believe that such a framework is an important stepping stone for bringing together definitions, highlighting open problems, connecting researchers willing to collaborate, and for unifying the arguably most significant search of this century.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00685v1
PDF	http://arxiv.org/pdf/1611.00685v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-searching-for-general
Repo
Framework

Scalable Compression of Deep Neural Networks


Title	Scalable Compression of Deep Neural Networks
Authors	Xing Wang, Jie Liang
Abstract	Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems. In this paper, we propose a scalable representation of the network parameters, so that different applications can select the most suitable bit rate of the network based on their own storage constraints. Moreover, when a device needs to upgrade to a high-rate network, the existing low-rate network can be reused, and only some incremental data are needed to be downloaded. We first hierarchically quantize the weights of a pre-trained deep neural network to enforce weight sharing. Next, we adaptively select the bits assigned to each layer given the total bit budget. After that, we retrain the network to fine-tune the quantized centroids. Experimental results show that our method can achieve scalable compression with graceful degradation in the performance.
Tasks
Published	2016-08-26
URL	http://arxiv.org/abs/1608.07365v1
PDF	http://arxiv.org/pdf/1608.07365v1.pdf
PWC	https://paperswithcode.com/paper/scalable-compression-of-deep-neural-networks
Repo
Framework

Attend, Infer, Repeat: Fast Scene Understanding with Generative Models


Title	Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
Authors	S. M. Ali Eslami, Nicolas Heess, Theophane Weber, Yuval Tassa, David Szepesvari, Koray Kavukcuoglu, Geoffrey E. Hinton
Abstract	We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D models (probabilistic renderers). We show that such models learn to identify multiple objects - counting, locating and classifying the elements of a scene - without any supervision, e.g., decomposing 3D images with various numbers of objects in a single forward pass of a neural network. We further show that the networks produce accurate inferences when compared to supervised counterparts, and that their structure leads to improved generalization.
Tasks	Scene Understanding
Published	2016-03-28
URL	http://arxiv.org/abs/1603.08575v3
PDF	http://arxiv.org/pdf/1603.08575v3.pdf
PWC	https://paperswithcode.com/paper/attend-infer-repeat-fast-scene-understanding
Repo
Framework

Automatic Selection of the Optimal Local Feature Detector


Title	Automatic Selection of the Optimal Local Feature Detector
Authors	Bruno Ferrarini, Shoaib Ehsan, Naveed Ur Rehman, Ales Leonardis, Klaus D. McDonald-Maier
Abstract	A large number of different feature detectors has been proposed so far. Any existing approach presents strengths and weaknesses, which make a detector optimal only for a limited range of applications. A tool capable of selecting the optimal feature detector in relation to the operating conditions is presented in this paper. The input images are quickly analyzed to determine what type of image transformation is applied to them and at which amount. Finally, the detector that is expected to obtain the highest repeatability under such conditions, is chosen to extract features from the input images. The efficiency and the good accuracy in determining the optimal feature detector for any operating condition, make the proposed tool suitable to be utilized in real visual applications. %A large number of different feature detectors has been proposed so far. Any existing approach presents strengths and weaknesses, which make a detector optimal only for a limited range of applications. A large number of different local feature detectors have been proposed in the last few years. However, each feature detector has its own strengths ad weaknesses that limit its use to a specific range of applications. In this paper is presented a tool capable of quickly analysing input images to determine which type and amount of transformation is applied to them and then selecting the optimal feature detector, which is expected to perform the best. The results show that the performance and the fast execution time render the proposed tool suitable for real-world vision applications.
Tasks
Published	2016-05-19
URL	http://arxiv.org/abs/1605.06094v1
PDF	http://arxiv.org/pdf/1605.06094v1.pdf
PWC	https://paperswithcode.com/paper/automatic-selection-of-the-optimal-local
Repo
Framework