January 29, 2020

3145 words 15 mins read

Paper Group ANR 663

Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks. Genetic Algorithms and the Traveling Salesman Problem a historical Review. The PRIMPing Routine – Tiling through Proximal Alternating Linearized Minimization. Black-box Adversarial ML Attack on Modulation Classification. PuckNet: Estimating hockey p …

Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks


Title	Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks
Authors	Ziling Wu, Abdulaziz Alorf, Ting Yang, Ling Li, Yunhui Zhu
Abstract	Convolutional Neural Networks (CNN) based image reconstruction methods have been intensely used for X-ray computed tomography (CT) reconstruction applications. Despite great success, good performance of this data-based approach critically relies on a representative big training data set and a dense convoluted deep network. The indiscriminating convolution connections over all dense layers could be prone to over-fitting, where sampling biases are wrongly integrated as features for the reconstruction. In this paper, we report a robust hierarchical synthesis reconstruction approach, where training data is pre-processed to separate the information on the domains where sampling biases are suspected. These split bands are then trained separately and combined successively through a hierarchical synthesis network. We apply the hierarchical synthesis reconstruction for two important and classical tomography reconstruction scenarios: the spares-view reconstruction and the phase reconstruction. Our simulated and experimental results show that comparable or improved performances are achieved with a dramatic reduction of network complexity and computational cost. This method can be generalized to a wide range of applications including material characterization, in-vivo monitoring and dynamic 4D imaging.
Tasks	Computed Tomography (CT), Image Reconstruction
Published	2019-01-30
URL	http://arxiv.org/abs/1901.10644v1
PDF	http://arxiv.org/pdf/1901.10644v1.pdf
PWC	https://paperswithcode.com/paper/robust-x-ray-sparse-view-phase-tomography-via
Repo
Framework

Genetic Algorithms and the Traveling Salesman Problem a historical Review


Title	Genetic Algorithms and the Traveling Salesman Problem a historical Review
Authors	Jan Scholz
Abstract	In this paper a highly abstracted view on the historical development of Genetic Algorithms for the Traveling Salesman Problem is given. In a meta-data analysis three phases in the development can be distinguished. First exponential growth in interest till 1996 can be observed, growth stays linear till 2011 and after that publications deteriorate. These three phases are examined and the major milestones are presented. Lastly an outlook to future work in this field is infered.
Tasks
Published	2019-01-17
URL	http://arxiv.org/abs/1901.05737v1
PDF	http://arxiv.org/pdf/1901.05737v1.pdf
PWC	https://paperswithcode.com/paper/genetic-algorithms-and-the-traveling-salesman
Repo
Framework

The PRIMPing Routine – Tiling through Proximal Alternating Linearized Minimization


Title	The PRIMPing Routine – Tiling through Proximal Alternating Linearized Minimization
Authors	Sibylle Hess, Katharina Morik, Nico Piatkowski
Abstract	Mining and exploring databases should provide users with knowledge and new insights. Tiles of data strive to unveil true underlying structure and distinguish valuable information from various kinds of noise. We propose a novel Boolean matrix factorization algorithm to solve the tiling problem, based on recent results from optimization theory. In contrast to existing work, the new algorithm minimizes the description length of the resulting factorization. This approach is well known for model selection and data compression, but not for finding suitable factorizations via numerical optimization. We demonstrate the superior robustness of the new approach in the presence of several kinds of noise and types of underlying structure. Moreover, our general framework can work with any cost measure having a suitable real-valued relaxation. Thereby, no convexity assumptions have to be met. The experimental results on synthetic data and image data show that the new method identifies interpretable patterns which explain the data almost always better than the competing algorithms.
Tasks	Model Selection
Published	2019-06-17
URL	https://arxiv.org/abs/1906.09722v1
PDF	https://arxiv.org/pdf/1906.09722v1.pdf
PWC	https://paperswithcode.com/paper/the-primping-routine-tiling-through-proximal
Repo
Framework

Black-box Adversarial ML Attack on Modulation Classification


Title	Black-box Adversarial ML Attack on Modulation Classification
Authors	Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha
Abstract	Recently, many deep neural networks (DNN) based modulation classification schemes have been proposed in the literature. We have evaluated the robustness of two famous such modulation classifiers (based on the techniques of convolutional neural networks and long short term memory) against adversarial machine learning attacks in black-box settings. We have used Carlini & Wagner (C-W) attack for performing the adversarial attack. To the best of our knowledge, the robustness of these modulation classifiers has not been evaluated through C-W attack before. Our results clearly indicate that state-of-art deep machine learning-based modulation classifiers are not robust against adversarial attacks.
Tasks	Adversarial Attack
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00635v1
PDF	https://arxiv.org/pdf/1908.00635v1.pdf
PWC	https://paperswithcode.com/paper/black-box-adversarial-ml-attack-on-modulation
Repo
Framework

PuckNet: Estimating hockey puck location from broadcast video


Title	PuckNet: Estimating hockey puck location from broadcast video
Authors	Kanav Vats, William McNally, Chris Dulhanty, Zhong Qiu Lin, David A. Clausi, John Zelek
Abstract	Puck location in ice hockey is essential for hockey analysts for determining the location of play and analyzing game events. However, because of the difficulty involved in obtaining accurate annotations due to the extremely low visibility and commonly occurring occlusions of the puck, the problem is very challenging. The problem becomes even more challenging in broadcast videos with changing camera angles. We introduce a novel methodology for determining puck location from approximate puck location annotations in broadcast video. Our method uniquely leverages the existing puck location information that is publicly available in existing hockey event data and uses the corresponding one-second broadcast video clips as input to the network. The rationale behind using video as input instead of static images is that with video, the temporal information can be utilized to handle puck occlusions. The network outputs a heatmap representing the probability of the puck location using a 3D CNN based architecture. The network is able to regress the puck location from broadcast hockey video clips with varying camera angles. Experimental results demonstrate the capability of the method, achieving 47.07% AUC on the test dataset. The network is also able to estimate the puck location in defensive/offensive zones with an accuracy of greater than 80%.
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05107v1
PDF	https://arxiv.org/pdf/1912.05107v1.pdf
PWC	https://paperswithcode.com/paper/pucknet-estimating-hockey-puck-location-from
Repo
Framework

Factors for the Generalisation of Identity Relations by Neural Networks


Title	Factors for the Generalisation of Identity Relations by Neural Networks
Authors	Radha Kopparti, Tillman Weyde
Abstract	Many researchers implicitly assume that neural networks learn relations and generalise them to new unseen data. It has been shown recently, however, that the generalisation of feed-forward networks fails for identity relations.The proposed solution for this problem is to create an inductive bias with Differential Rectifier (DR) units. In this work we explore various factors in the neural network architecture and learning process whether they make a difference to the generalisation on equality detection of Neural Networks without and and with DR units in early and mid fusion architectures. We find in experiments with synthetic data effects of the number of hidden layers, the activation function and the data representation. The training set size in relation to the total possible set of vectors also makes a difference. However, the accuracy never exceeds 61% without DR units at 50% chance level. DR units improve generalisation in all tasks and lead to almost perfect test accuracy in the Mid Fusion setting. Thus, DR units seem to be a promising approach for creating generalisation abilities that standard networks lack.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05449v1
PDF	https://arxiv.org/pdf/1906.05449v1.pdf
PWC	https://paperswithcode.com/paper/factors-for-the-generalisation-of-identity
Repo
Framework

Edge Correlations in Multilayer Networks


Title	Edge Correlations in Multilayer Networks
Authors	A. Roxana Pamfil, Sam D. Howison, Mason A. Porter
Abstract	Many recent developments in network analysis have focused on multilayer networks, which one can use to encode time-dependent interactions, multiple types of interactions, and other complications that arise in complex systems. Like their monolayer counterparts, multilayer networks in applications often have mesoscale features, such as community structure. A prominent type of method for inferring such structures is the employment of multilayer stochastic block models (SBMs). A common (but inadequate) assumption of these models is the sampling of edges in different layers independently, conditioned on community labels of the nodes. In this paper, we relax this assumption of independence by incorporating edge correlations into an SBM-like model. We derive maximum-likelihood estimates of the key parameters of our model, and we propose a measure of layer correlation that reflects the similarity between connectivity patterns in different layers. Finally, we explain how to use correlated models for edge prediction in multilayer networks. By taking into account edge correlations, prediction accuracy improves both in synthetic networks and in a temporal network of shoppers who are connected to previously-purchased grocery products.
Tasks
Published	2019-08-11
URL	https://arxiv.org/abs/1908.03875v1
PDF	https://arxiv.org/pdf/1908.03875v1.pdf
PWC	https://paperswithcode.com/paper/edge-correlations-in-multilayer-networks
Repo
Framework

High-dimensional Metric Combining for Non-coherent Molecular Signal Detection


Title	High-dimensional Metric Combining for Non-coherent Molecular Signal Detection
Authors	Zhuangkun Wei, Weisi Guo, Bin Li, Jerome Charmet, Chenglin Zhao
Abstract	In emerging Internet-of-Nano-Thing (IoNT), information will be embedded and conveyed in the form of molecules through complex and diffusive medias. One main challenge lies in the long-tail nature of the channel response causing inter-symbol-interference (ISI), which deteriorates the detection performance. If the channel is unknown, we cannot easily achieve traditional coherent channel estimation and cancellation, and the impact of ISI will be more severe. In this paper, we develop a novel high-dimensional non-coherent scheme for blind detection of molecular signals. We achieve this in a higher-dimensional metric space by combining different non-coherent metrics that exploit the transient features of the signals. By deducing the theoretical bit error rate (BER) for any constructed high-dimensional non-coherent metric, we prove that, higher dimensionality always achieves a lower BER in the same sample space. Then, we design a generalised blind detection algorithm that utilizes the Parzen approximation and its probabilistic neural network (Parzen-PNN) to detect information bits. Taking advantages of its fast convergence and parallel implementation, our proposed scheme can meet the needs of detection accuracy and real-time computing. Numerical simulations demonstrate that our proposed scheme can gain 10dB BER compared with other state of the art methods.
Tasks
Published	2019-01-31
URL	http://arxiv.org/abs/1901.11422v1
PDF	http://arxiv.org/pdf/1901.11422v1.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-metric-combining-for-non
Repo
Framework

Meta-heuristic for non-homogeneous peak density spaces and implementation on 2 real-world parameter learning/tuning applications


Title	Meta-heuristic for non-homogeneous peak density spaces and implementation on 2 real-world parameter learning/tuning applications
Authors	Mojtaba Moattari, Emad Roshandel, Shima Kamyab, Zohreh Azimifar
Abstract	Observer effect in physics (/psychology) regards bias in measurement (/perception) due to the interference of instrument (/knowledge). Based on these concepts, a new meta-heuristic algorithm is proposed for controlling memory usage per localities without pursuing Tabu-like cut-off approaches. In this paper, first, variations of observer effect are explained in different branches of science from physics to psychology. Then, a metaheuristic algorithm is proposed based on observer effect concepts and the used metrics are explained. The derived optimizer performance has been compared between 1st, non-homogeneous-peaks-density functions, and 2nd, homogeneous-peaks-density functions to verify the algorithm outperformance in the 1st scheme. Finally, performance analysis of the novel algorithms is derived using two real-world engineering applications in Electroencephalogram feature learning and Distributed Generator parameter tuning, each of which having nonlinearity and complex multi-modal peaks distributions as its characteristics. Also, the effect of version improvement has been assessed. The performance analysis among other optimizers in the same context suggests that the proposed algorithm is useful both solely and in hybrid Gradient Descent settings where problem’s search space is nonhomogeneous in terms of local peaks density.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05516v1
PDF	https://arxiv.org/pdf/1906.05516v1.pdf
PWC	https://paperswithcode.com/paper/meta-heuristic-for-non-homogeneous-peak
Repo
Framework

Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements


Title	Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements
Authors	Sheng Xu, Zhou Fan
Abstract	We consider estimating a piecewise-constant image, or a gradient-sparse signal on a general graph, from noisy linear measurements. We propose and study an iterative algorithm to minimize a penalized least-squares objective, with a penalty given by the “l_0-norm” of the signal’s discrete graph gradient. The method proceeds by approximate proximal descent, applying the alpha-expansion procedure to minimize a proximal gradient in each iteration, and using a geometric decay of the penalty parameter across iterations. Under a cut-restricted isometry property for the measurement design, we prove global recovery guarantees for the estimated signal. For standard Gaussian designs, the required number of measurements is independent of the graph structure, and improves upon worst-case guarantees for total-variation (TV) compressed sensing on the 1-D and 2-D lattice graphs by polynomial and logarithmic factors, respectively. The method empirically yields lower mean-squared recovery error compared with TV regularization in regimes of moderate undersampling and moderate to high signal-to-noise, for several examples of changepoint signals and gradient-sparse phantom images.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06097v1
PDF	https://arxiv.org/pdf/1905.06097v1.pdf
PWC	https://paperswithcode.com/paper/iterative-alpha-expansion-for-estimating
Repo
Framework

Relation Graph Network for 3D Object Detection in Point Clouds


Title	Relation Graph Network for 3D Object Detection in Point Clouds
Authors	Mingtao Feng, Syed Zulqarnain Gilani, Yaonan Wang, Liang Zhang, Ajmal Mian
Abstract	Convolutional Neural Networks (CNNs) have emerged as a powerful strategy for most object detection tasks on 2D images. However, their power has not been fully realised for detecting 3D objects in point clouds directly without converting them to regular grids. Existing state-of-art 3D object detection methods aim to recognize 3D objects individually without exploiting their relationships during learning or inference. In this paper, we first propose a strategy that associates the predictions of direction vectors and pseudo geometric centers together leading to a win-win solution for 3D bounding box candidates regression. Secondly, we propose point attention pooling to extract uniform appearance features for each 3D object proposal, benefiting from the learned direction features, semantic features and spatial coordinates of the object points. Finally, the appearance features are used together with the position features to build 3D object-object relationship graphs for all proposals to model their co-existence. We explore the effect of relation graphs on proposals’ appearance features enhancement under supervised and unsupervised settings. The proposed relation graph network consists of a 3D object proposal generation module and a 3D relation module, makes it an end-to-end trainable network for detecting 3D object in point clouds. Experiments on challenging benchmarks ( SunRGB-Dand ScanNet datasets ) of 3D point clouds show that our algorithm can perform better than the existing state-of-the-art methods.
Tasks	3D Object Detection, Object Detection, Object Proposal Generation
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00202v1
PDF	https://arxiv.org/pdf/1912.00202v1.pdf
PWC	https://paperswithcode.com/paper/relation-graph-network-for-3d-object
Repo
Framework

Neural Style Transfer for Point Clouds


Title	Neural Style Transfer for Point Clouds
Authors	Xu Cao, Weimin Wang, Katashi Nagao
Abstract	How can we edit or transform the geometric or color property of a point cloud? In this study, we propose a neural style transfer method for point clouds which allows us to transfer the style of geometry or color from one point cloud either independently or simultaneously to another. This transfer is achieved by manipulating the content representations and Gram-based style representations extracted from a pre-trained PointNet-based classification network for colored point clouds. As Gram-based style representation is invariant to the number or the order of points, the same method can be extended to transfer the style extracted from an image to the color expression of a point cloud by merely treating the image as a set of pixels. Experimental results demonstrate the capability of the proposed method for transferring style from either an image or a point cloud to another point cloud of a single object or even an indoor scene.
Tasks	Style Transfer
Published	2019-03-14
URL	http://arxiv.org/abs/1903.05807v1
PDF	http://arxiv.org/pdf/1903.05807v1.pdf
PWC	https://paperswithcode.com/paper/neural-style-transfer-for-point-clouds
Repo
Framework

Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding


Title	Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding
Authors	Nicholas R. Clayton, Hussein Abbass
Abstract	The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human to transfer the skills developed in designing reward functions to another human and in a systematic manner. In this paper, we use Systematic Instructional Design, an approach in human education, to engineer a machine education methodology to design reward functions for reinforcement learning. We demonstrate the methodology in designing a hierarchical genetic reinforcement learner that adopts a neural network representation to evolve a swarm controller for an agent shepherding a boids-based swarm. The results reveal that the methodology is able to guide the design of hierarchical reinforcement learners, with each model in the hierarchy learning incrementally through a multi-part reward function. The hierarchy acts as a decision fusion function that combines the individual behaviours and skills learnt by each instruction to create a smart shepherd to control the swarm.
Tasks
Published	2019-01-04
URL	http://arxiv.org/abs/1901.00949v1
PDF	http://arxiv.org/pdf/1901.00949v1.pdf
PWC	https://paperswithcode.com/paper/machine-teaching-in-hierarchical-genetic
Repo
Framework

Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers


Title	Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers
Authors	Shady Abu Hussein, Tom Tirer, Raja Giryes
Abstract	The single image super-resolution task is one of the most examined inverse problems in the past decade. In the recent years, Deep Neural Networks (DNNs) have shown superior performance over alternative methods when the acquisition process uses a fixed known downsampling kernel-typically a bicubic kernel. However, several recent works have shown that in practical scenarios, where the test data mismatch the training data (e.g. when the downsampling kernel is not the bicubic kernel or is not available at training), the leading DNN methods suffer from a huge performance drop. Inspired by the literature on generalized sampling, in this work we propose a method for improving the performance of DNNs that have been trained with a fixed kernel on observations acquired by other kernels. For a known kernel, we design a closed-form correction filter that modifies the low-resolution image to match one which is obtained by another kernel (e.g. bicubic), and thus improves the results of existing pre-trained DNNs. For an unknown kernel, we extend this idea and propose an algorithm for blind estimation of the required correction filter. We show that our approach outperforms other super-resolution methods, which are designed for general downsampling kernels.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00157v1
PDF	https://arxiv.org/pdf/1912.00157v1.pdf
PWC	https://paperswithcode.com/paper/correction-filter-for-single-image-super
Repo
Framework

Dense Morphological Network: An Universal Function Approximator


Title	Dense Morphological Network: An Universal Function Approximator
Authors	Ranjan Mondal, Sanchayan Santra, Bhabatosh Chanda
Abstract	Artificial neural networks are built on the basic operation of linear combination and non-linear activation function. Theoretically this structure can approximate any continuous function with three layer architecture. But in practice learning the parameters of such network can be hard. Also the choice of activation function can greatly impact the performance of the network. In this paper we are proposing to replace the basic linear combination operation with non-linear operations that do away with the need of additional non-linear activation function. To this end we are proposing the use of elementary morphological operations (dilation and erosion) as the basic operation in neurons. We show that these networks (Denoted as DenMo-Net) with morphological operations can approximate any smooth function requiring less number of parameters than what is necessary for normal neural networks. The results show that our network perform favorably when compared with similar structured network.
Tasks	Representation Learning
Published	2019-01-01
URL	https://arxiv.org/abs/1901.00109v2
PDF	https://arxiv.org/pdf/1901.00109v2.pdf
PWC	https://paperswithcode.com/paper/dense-morphological-network-an-universal
Repo
Framework