Paper Group ANR 488
GPU based Parallel Optimization for Real Time Panoramic Video Stitching. Generalized Content-Preserving Warps for Image Stitching. Feature-less Stitching of Cylindrical Tunnel. Towards an Intelligent Edge: Wireless Communication Meets Machine Learning. Gene Shaving using influence function of a kernel method. Mitigating Planner Overfitting in Model …
GPU based Parallel Optimization for Real Time Panoramic Video Stitching
| Title | GPU based Parallel Optimization for Real Time Panoramic Video Stitching |
| Authors | Chengyao Du, Jingling Yuan, Jiansheng Dong, Lin Li, Mincheng Chen, Tao Li |
| Abstract | Panoramic video is a sort of video recorded at the same point of view to record the full scene. With the development of video surveillance and the requirement for 3D converged video surveillance in smart cities, CPU and GPU are required to possess strong processing abilities to make panoramic video. The traditional panoramic products depend on post processing, which results in high power consumption, low stability and unsatisfying performance in real time. In order to solve these problems,we propose a real-time panoramic video stitching framework.The framework we propose mainly consists of three algorithms, LORB image feature extraction algorithm, feature point matching algorithm based on LSH and GPU parallel video stitching algorithm based on CUDA.The experiment results show that the algorithm mentioned can improve the performance in the stages of feature extraction of images stitching and matching, the running speed of which is 11 times than that of the traditional ORB algorithm and 639 times than that of the traditional SIFT algorithm. Based on analyzing the GPU resources occupancy rate of each resolution image stitching, we further propose a stream parallel strategy to maximize the utilization of GPU resources. Compared with the L-ORB algorithm, the efficiency of this strategy is improved by 1.6-2.5 times, and it can make full use of GPU resources. The performance of the system accomplished in the paper is 29.2 times than that of the former embedded one, while the power dissipation is reduced to 10W. |
| Tasks | Image Stitching |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.03988v2 |
| http://arxiv.org/pdf/1810.03988v2.pdf | |
| PWC | https://paperswithcode.com/paper/gpu-based-parallel-optimization-for-real-time |
| Repo | |
| Framework | |
Generalized Content-Preserving Warps for Image Stitching
| Title | Generalized Content-Preserving Warps for Image Stitching |
| Authors | Kai Chen, Jingmin Tu, Jian Yao |
| Abstract | Local misalignment caused by global homography is a common issue in image stitching task. Content-Preserving Warping (CPW) is a typical method to deal with this issue, in which geometric and photometric constraints are imposed to guide the warping process. One of its essential condition however, is colour consistency, and an elusive goal in real world applications. In this paper, we propose a Generalized Content-Preserving Warping (GCPW) method to alleviate this problem. GCPW extends the original CPW by applying a colour model that expresses the colour transformation between images locally, thus meeting the photometric constraint requirements for effective image stitching. We combine the photometric and geometric constraints and jointly estimate the colour transformation and the warped mesh vertexes, simultaneously. We align images locally with an optimal grid mesh generated by our GCPW method. Experiments on both synthetic and real images demonstrate that our new method is robust to colour variations, outperforming other state-of-the-art CPW-based image stitching methods. |
| Tasks | Image Stitching |
| Published | 2018-09-18 |
| URL | http://arxiv.org/abs/1809.06783v1 |
| http://arxiv.org/pdf/1809.06783v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-content-preserving-warps-for |
| Repo | |
| Framework | |
Feature-less Stitching of Cylindrical Tunnel
| Title | Feature-less Stitching of Cylindrical Tunnel |
| Authors | Ramanpreet Singh Pahwa, Wei Kiat Leong, Shaohui Foong, Karianto Leman, Minh N. Do |
| Abstract | Traditional image stitching algorithms use transforms such as homography to combine different views of a scene. They usually work well when the scene is planar or when the camera is only rotated, keeping its position static. This severely limits their use in real world scenarios where an unmanned aerial vehicle (UAV) potentially hovers around and flies in an enclosed area while rotating to capture a video sequence. We utilize known scene geometry along with recorded camera trajectory to create cylindrical images captured in a given environment such as a tunnel where the camera rotates around its center. The captured images of the inner surface of the given scene are combined to create a composite panoramic image that is textured onto a 3D geometrical object in Unity graphical engine to create an immersive environment for end users. |
| Tasks | Image Stitching |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10278v1 |
| http://arxiv.org/pdf/1806.10278v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-less-stitching-of-cylindrical-tunnel |
| Repo | |
| Framework | |
Towards an Intelligent Edge: Wireless Communication Meets Machine Learning
| Title | Towards an Intelligent Edge: Wireless Communication Meets Machine Learning |
| Authors | Guangxu Zhu, Dongzhu Liu, Yuqing Du, Changsheng You, Jun Zhang, Kaibin Huang |
| Abstract | The recent revival of artificial intelligence (AI) is revolutionizing almost every branch of science and technology. Given the ubiquitous smart mobile gadgets and Internet of Things (IoT) devices, it is expected that a majority of intelligent applications will be deployed at the edge of wireless networks. This trend has generated strong interests in realizing an “intelligent edge” to support AI-enabled applications at various edge devices. Accordingly, a new research area, called edge learning, emerges, which crosses and revolutionizes two disciplines: wireless communication and machine learning. A major theme in edge learning is to overcome the limited computing power, as well as limited data, at each edge device. This is accomplished by leveraging the mobile edge computing (MEC) platform and exploiting the massive data distributed over a large number of edge devices. In such systems, learning from distributed data and communicating between the edge server and devices are two critical and coupled aspects, and their fusion poses many new research challenges. This article advocates a new set of design principles for wireless communication in edge learning, collectively called learning-driven communication. Illustrative examples are provided to demonstrate the effectiveness of these design principles, and unique research opportunities are identified. |
| Tasks | |
| Published | 2018-09-02 |
| URL | http://arxiv.org/abs/1809.00343v1 |
| http://arxiv.org/pdf/1809.00343v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-an-intelligent-edge-wireless |
| Repo | |
| Framework | |
Gene Shaving using influence function of a kernel method
| Title | Gene Shaving using influence function of a kernel method |
| Authors | Md. Ashad Alam, Mohammad Shahjama, Md. Ferdush Rahman |
| Abstract | Identifying significant subsets of the genes, gene shaving is an essential and challenging issue for biomedical research for a huge number of genes and the complex nature of biological networks,. Since positive definite kernel based methods on genomic information can improve the prediction of diseases, in this paper we proposed a new method, “kernel gene shaving (kernel canonical correlation analysis (kernel CCA) based gene shaving). This problem is addressed using the influence function of the kernel CCA. To investigate the performance of the proposed method in a comparison of three popular gene selection methods (T-test, SAM and LIMMA), we were used extensive simulated and real microarray gene expression datasets. The performance measures AUC was computed for each of the methods. The achievement of the proposed method has improved than the three well-known gene selection methods. In real data analysis, the proposed method identified a subsets of $210$ genes out of $2000$ genes. The network of these genes has significantly more interactions than expected, which indicates that they may function in a concerted effort on colon cancer. |
| Tasks | |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01625v1 |
| http://arxiv.org/pdf/1809.01625v1.pdf | |
| PWC | https://paperswithcode.com/paper/gene-shaving-using-influence-function-of-a |
| Repo | |
| Framework | |
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
| Title | Mitigating Planner Overfitting in Model-Based Reinforcement Learning |
| Authors | Dilip Arumugam, David Abel, Kavosh Asadi, Nakul Gopalan, Christopher Grimm, Jun Ki Lee, Lucas Lehnert, Michael L. Littman |
| Abstract | An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model. Alternatively, it can take a more conservative stance and eschew its model in favor of optimizing its behavior solely via real-world interaction. This latter approach can be exceedingly slow to learn from experience, while the former can lead to “planner overfitting” - aspects of the agent’s behavior are optimized to exploit errors in its model. This paper explores an intermediate position in which the planner seeks to avoid overfitting through a kind of regularization of the plans it considers. We present three different approaches that demonstrably mitigate planner overfitting in reinforcement-learning environments. |
| Tasks | |
| Published | 2018-12-03 |
| URL | https://arxiv.org/abs/1812.01129v2 |
| https://arxiv.org/pdf/1812.01129v2.pdf | |
| PWC | https://paperswithcode.com/paper/mitigating-planner-overfitting-in-model-based |
| Repo | |
| Framework | |
Forensic Discrimination between Traditional and Compressive Imaging Systems
| Title | Forensic Discrimination between Traditional and Compressive Imaging Systems |
| Authors | Ali Taimori, Farokh Marvasti |
| Abstract | Compressive sensing is a new technology for modern computational imaging systems. In comparison to widespread conventional image sensing, the compressive imaging paradigm requires specific forensic analysis techniques and tools. In this regards, one of basic scenarios in image forensics is to distinguish traditionally sensed images from sophisticated compressively sensed ones. To do this, we first mathematically and systematically model the imaging system based on compressive sensing technology. Afterwards, a simplified version of the whole model is presented, which is appropriate for forensic investigation applications. We estimate the nonlinear system of compressive sensing with a linear model. Then, we model the imaging pipeline as an inverse problem and demonstrate that different imagers have discriminative degradation kernels. Hence, blur kernels of various imaging systems have utilized as footprints for discriminating image acquisition sources. In order to accomplish the identification cycle, we have utilized the state-of-the-art Convolutional Neural Network (CNN) and Support Vector Machine (SVM) approaches to learn a classification system from estimated blur kernels. Numerical experiments show promising identification results. Simulation codes are available for research and development purposes. |
| Tasks | Compressive Sensing |
| Published | 2018-11-07 |
| URL | http://arxiv.org/abs/1811.03157v1 |
| http://arxiv.org/pdf/1811.03157v1.pdf | |
| PWC | https://paperswithcode.com/paper/forensic-discrimination-between-traditional |
| Repo | |
| Framework | |
Pontogammarus Maeoticus Swarm Optimization: A Metaheuristic Optimization Algorithm
| Title | Pontogammarus Maeoticus Swarm Optimization: A Metaheuristic Optimization Algorithm |
| Authors | Benyamin Ghojogh, Saeed Sharifian |
| Abstract | Nowadays, metaheuristic optimization algorithms are used to find the global optima in difficult search spaces. Pontogammarus Maeoticus Swarm Optimization (PMSO) is a metaheuristic algorithm imitating aquatic nature and foraging behavior. Pontogammarus Maeoticus, also called Gammarus in short, is a tiny creature found mostly in coast of Caspian Sea in Iran. In this algorithm, global optima is modeled as sea edge (coast) to which Gammarus creatures are willing to move in order to rest from sea waves and forage in sand. Sea waves satisfy exploration and foraging models exploitation. The strength of sea wave is determined according to distance of Gammarus from sea edge. The angles of waves applied on several particles are set randomly helping algorithm not be stuck in local bests. Meanwhile, the neighborhood of particles change adaptively resulting in more efficient progress in searching. The proposed algorithm, although is applicable on any optimization problem, is experimented for partially shaded solar PV array. Experiments on CEC05 benchmarks, as well as solar PV array, show the effectiveness of this optimization algorithm. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.01844v1 |
| http://arxiv.org/pdf/1807.01844v1.pdf | |
| PWC | https://paperswithcode.com/paper/pontogammarus-maeoticus-swarm-optimization-a |
| Repo | |
| Framework | |
Learning Constraints from Demonstrations
| Title | Learning Constraints from Demonstrations |
| Authors | Glen Chou, Dmitry Berenson, Necmiye Ozay |
| Abstract | We extend the learning from demonstration paradigm by providing a method for learning unknown constraints shared across tasks, using demonstrations of the tasks, their cost functions, and knowledge of the system dynamics and control constraints. Given safe demonstrations, our method uses hit-and-run sampling to obtain lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a consistent representation of the unsafe set via solving an integer program. Our method generalizes across system dynamics and learns a guaranteed subset of the constraint. We also provide theoretical analysis on what subset of the constraint can be learnable from safe demonstrations. We demonstrate our method on linear and nonlinear system dynamics, show that it can be modified to work with suboptimal demonstrations, and that it can also be used to learn constraints in a feature space. |
| Tasks | |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.07084v2 |
| http://arxiv.org/pdf/1812.07084v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-constraints-from-demonstrations |
| Repo | |
| Framework | |
Resource-driven Substructural Defeasible Logic
| Title | Resource-driven Substructural Defeasible Logic |
| Authors | Francesco Olivieri, Guido Governatori, Matteo Cristani, Nick van Beest, Silvano Colombo-Tosatto |
| Abstract | Linear Logic and Defeasible Logic have been adopted to formalise different features relevant to agents: consumption of resources, and reasoning with exceptions. We propose a framework to combine sub-structural features, corresponding to the consumption of resources, with defeasibility aspects, and we discuss the design choices for the framework. |
| Tasks | |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.03656v1 |
| http://arxiv.org/pdf/1809.03656v1.pdf | |
| PWC | https://paperswithcode.com/paper/resource-driven-substructural-defeasible |
| Repo | |
| Framework | |
A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
| Title | A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving |
| Authors | Xiangyu Yue, Bichen Wu, Sanjit A. Seshia, Kurt Keutzer, Alberto L. Sangiovanni-Vincentelli |
| Abstract | 3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a significant amount of manual annotation. This jeopardizes the efficient development of supervised deep learning algorithms which are often data-hungry. We present a framework to rapidly create point clouds with accurate point-level labels from a computer game. The framework supports data collection from both auto-driving scenes and user-configured scenes. Point clouds from auto-driving scenes can be used as training data for deep learning algorithms, while point clouds from user-configured scenes can be used to systematically test the vulnerability of a neural network, and use the falsifying examples to make the neural network more robust through retraining. In addition, the scene images can be captured simultaneously in order for sensor fusion tasks, with a method proposed to do automatic calibration between the point clouds and captured scene images. We show a significant improvement in accuracy (+9%) in point cloud segmentation by augmenting the training dataset with the generated synthesized data. Our experiments also show by testing and retraining the network using point clouds from user-configured scenes, the weakness/blind spots of the neural network can be fixed. |
| Tasks | Autonomous Driving, Calibration, Sensor Fusion |
| Published | 2018-03-31 |
| URL | http://arxiv.org/abs/1804.00103v1 |
| http://arxiv.org/pdf/1804.00103v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-lidar-point-cloud-generator-from-a-virtual |
| Repo | |
| Framework | |
Visual Attention and its Intimate Links to Spatial Cognition
| Title | Visual Attention and its Intimate Links to Spatial Cognition |
| Authors | John K. Tsotsos, Iuliia Kotseruba, Amir Rasouli, Markus D. Solbach |
| Abstract | It is almost universal to regard attention as the facility that permits an agent, human or machine, to give priority processing resources to relevant stimuli while ignoring the irrelevant. The reality of how this might manifest itself throughout all the forms of perceptual and cognitive processes possessed by humans, however, is not as clear. Here we examine this reality with a broad perspective in order to highlight the myriad ways that attentional processes impact both perception and cognition. The paper concludes by showing two real world problems that exhibit sufficient complexity to illustrate the ways in which attention and cognition connect. These then point to new avenues of research that might illuminate the overall cognitive architecture of spatial cognition. |
| Tasks | |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11530v1 |
| http://arxiv.org/pdf/1806.11530v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-attention-and-its-intimate-links-to |
| Repo | |
| Framework | |
The Bregman chord divergence
| Title | The Bregman chord divergence |
| Authors | Frank Nielsen, Richard Nock |
| Abstract | Distances are fundamental primitives whose choice significantly impacts the performances of algorithms in machine learning and signal processing. However selecting the most appropriate distance for a given task is an endeavor. Instead of testing one by one the entries of an ever-expanding dictionary of {\em ad hoc} distances, one rather prefers to consider parametric classes of distances that are exhaustively characterized by axioms derived from first principles. Bregman divergences are such a class. However fine-tuning a Bregman divergence is delicate since it requires to smoothly adjust a functional generator. In this work, we propose an extension of Bregman divergences called the Bregman chord divergences. This new class of distances does not require gradient calculations, uses two scalar parameters that can be easily tailored in applications, and generalizes asymptotically Bregman divergences. |
| Tasks | |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09113v1 |
| http://arxiv.org/pdf/1810.09113v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-bregman-chord-divergence |
| Repo | |
| Framework | |
Weight Learning in a Probabilistic Extension of Answer Set Programs
| Title | Weight Learning in a Probabilistic Extension of Answer Set Programs |
| Authors | Joohyung Lee, Yi Wang |
| Abstract | LPMLN is a probabilistic extension of answer set programs with the weight scheme derived from that of Markov Logic. Previous work has shown how inference in LPMLN can be achieved. In this paper, we present the concept of weight learning in LPMLN and learning algorithms for LPMLN derived from those for Markov Logic. We also present a prototype implementation that uses answer set solvers for learning as well as some example domains that illustrate distinct features of LPMLN learning. Learning in LPMLN is in accordance with the stable model semantics, thereby it learns parameters for probabilistic extensions of knowledge-rich domains where answer set programming has shown to be useful but limited to the deterministic case, such as reachability analysis and reasoning about actions in dynamic domains. We also apply the method to learn the parameters for probabilistic abductive reasoning about actions. |
| Tasks | |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04527v2 |
| http://arxiv.org/pdf/1808.04527v2.pdf | |
| PWC | https://paperswithcode.com/paper/weight-learning-in-a-probabilistic-extension |
| Repo | |
| Framework | |
A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation
| Title | A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation |
| Authors | Surafel M. Lakew, Mauro Cettolo, Marcello Federico |
| Abstract | Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems. Notably, in low-resource settings, it proved to work effectively and efficiently, thanks to shared representation space that is forced across languages and induces a sort of transfer-learning. Furthermore, multilingual NMT enables so-called zero-shot inference across language pairs never seen at training time. Despite the increasing interest in this framework, an in-depth analysis of what a multilingual NMT model is capable of and what it is not is still missing. Motivated by this, our work (i) provides a quantitative and comparative analysis of the translations produced by bilingual, multilingual and zero-shot systems; (ii) investigates the translation quality of two of the currently dominant neural architectures in MT, which are the Recurrent and the Transformer ones; and (iii) quantitatively explores how the closeness between languages influences the zero-shot translation. Our analysis leverages multiple professional post-edits of automatic translations by several different systems and focuses both on automatic standard metrics (BLEU and TER) and on widely used error categories, which are lexical, morphology, and word order errors. |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2018-06-18 |
| URL | http://arxiv.org/abs/1806.06957v2 |
| http://arxiv.org/pdf/1806.06957v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-transformer-and-recurrent |
| Repo | |
| Framework | |
