January 31, 2020

3167 words 15 mins read

Paper Group ANR 9

Descriptive evaluation of students using fuzzy approximate reasoning. Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms. OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras. Towards Neural-Guided Program Synthesis for Linear Temporal Logic Specifications. SSA-CNN: Semantic Self-A …

Descriptive evaluation of students using fuzzy approximate reasoning


Title	Descriptive evaluation of students using fuzzy approximate reasoning
Authors	Mohsen Annabestani, Alireza Rowhanimanesh, Aylar Mizani, Akram Rezaei
Abstract	In recent years, descriptive evaluation has been introduced as a new model for educational evaluation of Iranian students. The current descriptive evaluation method is based on four-valued logic. Assessing all students with only four values is led to a lack of relative justice and the creation of unrealistic equality. Also, the complexity of the evaluation process in the current method increases teacher errors likelihood. As a suitable solution, in this paper, a fuzzy descriptive evaluation system has been proposed. The proposed method is based on fuzzy logic, which is an infinite-valued logic and it can perform approximate reasoning on natural language propositions. By the proposed fuzzy system, student assessment is performed over the school year with infinite values instead of four values. But to eliminate the diversity of assigned values to students, at the end of the school year, the calculated values for each student will be rounded to the nearest value of the four standard values of the current descriptive evaluation system. It can be implemented easily in an appropriate smartphone app, which makes it much easier for the teachers to evaluate the evaluation process. In this paper, the evaluation process of the elementary third-grade mathematics course in Iran during the period from the beginning of the MEHR (The Seventh month of Iran) to the end of BAHMAN (The Eleventh Month of Iran) is examined by the proposed system. To evaluate the validity of this system, the proposed method has been simulated in MATLAB software.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02549v2
PDF	https://arxiv.org/pdf/1905.02549v2.pdf
PWC	https://paperswithcode.com/paper/descriptive-evaluation-of-students-using
Repo
Framework

Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms


Title	Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms
Authors	Shahana Ibrahim, Xiao Fu, Nikos Kargas, Kejun Huang
Abstract	The data deluge comes with high demands for data labeling. Crowdsourcing (or, more generally, ensemble learning) techniques aim to produce accurate labels via integrating noisy, non-expert labeling from annotators. The classic Dawid-Skene estimator and its accompanying expectation maximization (EM) algorithm have been widely used, but the theoretical properties are not fully understood. Tensor methods were proposed to guarantee identification of the Dawid-Skene model, but the sample complexity is a hurdle for applying such approaches—since the tensor methods hinge on the availability of third-order statistics that are hard to reliably estimate given limited data. In this paper, we propose a framework using pairwise co-occurrences of the annotator responses, which naturally admits lower sample complexity. We show that the approach can identify the Dawid-Skene model under realistic conditions. We propose an algebraic algorithm reminiscent of convex geometry-based structured matrix factorization to solve the model identification problem efficiently, and an identifiability-enhanced algorithm for handling more challenging and critical scenarios. Experiments show that the proposed algorithms outperform the state-of-art algorithms under a variety of scenarios.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12325v1
PDF	https://arxiv.org/pdf/1909.12325v1.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-via-pairwise-co-occurrences
Repo
Framework

OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras


Title	OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras
Authors	G. Dias Pais, Tiago J. Dias, Jacinto C. Nascimento, Pedro Miraldo
Abstract	Pedestrian detection is one of the most explored topics in computer vision and robotics. The use of deep learning methods allowed the development of new and highly competitive algorithms. Deep Reinforcement Learning has proved to be within the state-of-the-art in terms of both detection in perspective cameras and robotics applications. However, for detection in omnidirectional cameras, the literature is still scarce, mostly because of their high levels of distortion. This paper presents a novel and efficient technique for robust pedestrian detection in omnidirectional images. The proposed method uses deep Reinforcement Learning that takes advantage of the distortion in the image. By considering the 3D bounding boxes and their distorted projections into the image, our method is able to provide the pedestrian’s position in the world, in contrast to the image positions provided by most state-of-the-art methods for perspective cameras. Our method avoids the need of pre-processing steps to remove the distortion, which is computationally expensive. Beyond the novel solution, our method compares favorably with the state-of-the-art methodologies that do not consider the underlying distortion for the detection task.
Tasks	Pedestrian Detection
Published	2019-03-02
URL	http://arxiv.org/abs/1903.00676v1
PDF	http://arxiv.org/pdf/1903.00676v1.pdf
PWC	https://paperswithcode.com/paper/omnidrl-robust-pedestrian-detection-using
Repo
Framework

Towards Neural-Guided Program Synthesis for Linear Temporal Logic Specifications


Title	Towards Neural-Guided Program Synthesis for Linear Temporal Logic Specifications
Authors	Alberto Camacho, Sheila A. McIlraith
Abstract	Synthesizing a program that realizes a logical specification is a classical problem in computer science. We examine a particular type of program synthesis, where the objective is to synthesize a strategy that reacts to a potentially adversarial environment while ensuring that all executions satisfy a Linear Temporal Logic (LTL) specification. Unfortunately, exact methods to solve so-called LTL synthesis via logical inference do not scale. In this work, we cast LTL synthesis as an optimization problem. We employ a neural network to learn a Q-function that is then used to guide search, and to construct programs that are subsequently verified for correctness. Our method is unique in combining search with deep learning to realize LTL synthesis. In our experiments the learned Q-function provides effective guidance for synthesis problems with relatively small specifications.
Tasks	Program Synthesis
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13430v1
PDF	https://arxiv.org/pdf/1912.13430v1.pdf
PWC	https://paperswithcode.com/paper/towards-neural-guided-program-synthesis-for
Repo
Framework

SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection


Title	SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection
Authors	Chengju Zhou, Meiqing Wu, Siew-Kei Lam
Abstract	Pedestrian detection plays an important role in many applications such as autonomous driving. We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection performance. Specifically, a multi-task network is designed to jointly learn semantic segmentation and pedestrian detection from image datasets with weak box-wise annotations. The semantic segmentation feature maps are concatenated with corresponding convolution features maps to provide more discriminative features for pedestrian detection and pedestrian classification. By jointly learning segmentation and detection, our proposed pedestrian self-attention mechanism can effectively identify pedestrian regions and suppress backgrounds. In addition, we propose to incorporate semantic attention information from multi-scale layers into deep convolution neural network to boost pedestrian detection. Experiment results show that the proposed method achieves the best detection performance with MR of 6.27% on Caltech dataset and obtain competitive performance on CityPersons dataset while maintaining high computational efficiency.
Tasks	Autonomous Driving, Pedestrian Detection, Semantic Segmentation
Published	2019-02-25
URL	https://arxiv.org/abs/1902.09080v3
PDF	https://arxiv.org/pdf/1902.09080v3.pdf
PWC	https://paperswithcode.com/paper/ssa-cnn-semantic-self-attention-cnn-for
Repo
Framework

Learning Functional Dependencies with Sparse Regression


Title	Learning Functional Dependencies with Sparse Regression
Authors	Zhihan Guo, Theodoros Rekatsinas
Abstract	We study the problem of discovering functional dependencies (FD) from a noisy dataset. We focus on FDs that correspond to statistical dependencies in a dataset and draw connections between FD discovery and structure learning in probabilistic graphical models. We show that discovering FDs from a noisy dataset is equivalent to learning the structure of a graphical model over binary random variables, where each random variable corresponds to a functional of the dataset attributes. We build upon this observation to introduce AutoFD a conceptually simple framework in which learning functional dependencies corresponds to solving a sparse regression problem. We show that our methods can recover true functional dependencies across a diverse array of real-world and synthetic datasets, even in the presence of noisy or missing data. We find that AutoFD scales to large data instances with millions of tuples and hundreds of attributes while it yields an average F1 improvement of 2 times against state-of-the-art FD discovery methods.
Tasks
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01425v1
PDF	https://arxiv.org/pdf/1905.01425v1.pdf
PWC	https://paperswithcode.com/paper/learning-functional-dependencies-with-sparse
Repo
Framework

Learning over inherently distributed data


Title	Learning over inherently distributed data
Authors	Donghui Yan, Ying Xu
Abstract	The recent decades have seen a surge of interests in distributed computing. Existing work focus primarily on either distributed computing platforms, data query tools, or, algorithms to divide big data and conquer at individual machines etc. It is, however, increasingly often that the data of interest are inherently distributed, i.e., data are stored at multiple distributed sites due to diverse collection channels, business operations etc. We propose to enable learning and inference in such a setting via a general framework based on the distortion minimizing local transformations. This framework only requires a small amount of local signatures to be shared among distributed sites, eliminating the need of having to transmitting big data. Computation can be done very efficiently via parallel local computation. The error incurred due to distributed computing vanishes when increasing the size of local signatures. As the shared data need not be in their original form, data privacy may also be preserved. Experiments on linear (logistic) regression and Random Forests have shown promise of this approach. This framework is expected to apply to a general class of tools in learning and inference with the continuity property.
Tasks
Published	2019-07-30
URL	https://arxiv.org/abs/1907.13208v1
PDF	https://arxiv.org/pdf/1907.13208v1.pdf
PWC	https://paperswithcode.com/paper/learning-over-inherently-distributed-data
Repo
Framework

Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge


Title	Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge
Authors	Md Ashraful Alam Milton
Abstract	The main essence of this paper is to investigate the performance of RetinaNet based object detectors on pedestrian detection. Pedestrian detection is an important research topic as it provides a baseline for general object detection and has a great number of practical applications like autonomous car, robotics and Security camera. Though extensive research has made huge progress in pedestrian detection, there are still many issues and open for more research and improvement. Recent deep learning based methods have shown state-of-the-art performance in computer vision tasks such as image classification, object detection, and segmentation. Wider pedestrian detection challenge aims at finding improve solutions for pedestrian detection problem. In this paper, We propose a pedestrian detection system based on RetinaNet. Our solution has scored 0.4061 mAP. The code is available at https://github.com/miltonbd/ECCV_2018_pedestrian_detection_challenege.
Tasks	Image Classification, Object Detection, Pedestrian Detection
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01031v1
PDF	http://arxiv.org/pdf/1902.01031v1.pdf
PWC	https://paperswithcode.com/paper/towards-pedestrian-detection-using-retinanet
Repo
Framework

Vehicle detection and counting from VHR satellite images: efforts and open issues


Title	Vehicle detection and counting from VHR satellite images: efforts and open issues
Authors	Alice Froidevaux, Andréa Julier, Agustin Lifschitz, Minh-Tan Pham, Romain Dambreville, Sébastien Lefèvre, Pierre Lassalle, Thanh-Long Huynh
Abstract	Detection of new infrastructures (commercial, logistics, industrial or residential) from satellite images constitutes a proven method to investigate and follow economic and urban growth. The level of activities or exploitation of these sites may be hardly determined by building inspection, but could be inferred from vehicle presence from nearby streets and parking lots. We present in this paper two deep learning-based models for vehicle counting from optical satellite images coming from the Pleiades sensor at 50-cm spatial resolution. Both segmentation (Tiramisu) and detection (YOLO) architectures were investigated. These networks were adapted, trained and validated on a data set including 87k vehicles, annotated using an interactive semi-automatic tool developed by the authors. Experimental results show that both segmentation and detection models could achieve a precision rate higher than 85% with a recall rate also high (76.4% and 71.9% for Tiramisu and YOLO respectively).
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.10017v2
PDF	https://arxiv.org/pdf/1910.10017v2.pdf
PWC	https://paperswithcode.com/paper/vehicle-detection-and-counting-from-vhr
Repo
Framework

Grounding Human-to-Vehicle Advice for Self-driving Vehicles


Title	Grounding Human-to-Vehicle Advice for Self-driving Vehicles
Authors	Jinkyu Kim, Teruhisa Misu, Yi-Ting Chen, Ashish Tawari, John Canny
Abstract	Recent success suggests that deep neural control networks are likely to be a key component of self-driving vehicles. These networks are trained on large datasets to imitate human actions, but they lack semantic understanding of image contents. This makes them brittle and potentially unsafe in situations that do not match training data. Here, we propose to address this issue by augmenting training data with natural language advice from a human. Advice includes guidance about what to do and where to attend. We present the first step toward advice giving, where we train an end-to-end vehicle controller that accepts advice. The controller adapts the way it attends to the scene (visual attention) and the control (steering and speed). Attention mechanisms tie controller behavior to salient objects in the advice. We evaluate our model on a novel advisable driving dataset with manually annotated human-to-vehicle advice called Honda Research Institute-Advice Dataset (HAD). We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice. The dataset is available at https://usa.honda-ri.com/HAD.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06978v1
PDF	https://arxiv.org/pdf/1911.06978v1.pdf
PWC	https://paperswithcode.com/paper/grounding-human-to-vehicle-advice-for-self-1
Repo
Framework

Effects of lead position, cardiac rhythm variation and drug-induced QT prolongation on performance of machine learning methods for ECG processing


Title	Effects of lead position, cardiac rhythm variation and drug-induced QT prolongation on performance of machine learning methods for ECG processing
Authors	Marat Bogdanov, Salim Baigildin, Aygul Fabarisova, Konstantin Ushenin, Olga Solovyova
Abstract	Machine learning shows great performance in various problems of electrocardiography (ECG) signal analysis. However, collecting a dataset for biomedical engineering is a very difficult task. Any dataset for ECG processing contains from 100 to 10,000 times fewer cases than datasets for image or text analysis. This issue is especially important because of physiological phenomena that can significantly change the morphology of heartbeats in ECG signals. In this preliminary study, we analyze the effects of lead choice from the standard ECG recordings, variation of ECG during 24-hours, and the effects of QT-prolongation agents on the performance of machine learning methods for ECG processing. We choose the problem of subject identification for analysis, because this problem may be solved for almost any available dataset of ECG data. In a discussion, we compare our findings with observations from other works that use machine learning for ECG processing with different problem statements. Our results show the importance of training dataset enrichment with ECG signals acquired in specific physiological conditions for obtaining good performance of ECG processing for real applications.
Tasks	Electrocardiography (ECG)
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04672v2
PDF	https://arxiv.org/pdf/1912.04672v2.pdf
PWC	https://paperswithcode.com/paper/effects-of-lead-position-cardiac-rhythm
Repo
Framework

Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization


Title	Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization
Authors	Zhi Zhang, Jiachen Yang, Hongyuan Zha
Abstract	Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions. Recent studies applying deep reinforcement learning (RL) to optimize single traffic lights have shown significant improvement over conventional control. However, optimization of global traffic condition over a large road network fundamentally is a cooperative multi-agent control problem, for which single-agent RL is not suitable due to environment non-stationarity and infeasibility of optimizing over an exponential joint-action space. Motivated by these challenges, we propose QCOMBO, a simple yet effective multi-agent reinforcement learning (MARL) algorithm that combines the advantages of independent and centralized learning. We ensure scalability by selecting actions from individually optimized utility functions, which are shaped to maximize global performance via a novel consistency regularization loss between individual utility and a global action-value function. Experiments on diverse road topologies and traffic flow conditions in the SUMO traffic simulator show competitive performance of QCOMBO versus recent state-of-the-art MARL algorithms. We further show that policies trained on small sub-networks can effectively generalize to larger networks under different traffic flow conditions, providing empirical evidence for the suitability of MARL for intelligent traffic control.
Tasks	Multi-agent Reinforcement Learning
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10651v1
PDF	https://arxiv.org/pdf/1909.10651v1.pdf
PWC	https://paperswithcode.com/paper/integrating-independent-and-centralized-multi
Repo
Framework

Off-Policy Policy Gradient with State Distribution Correction


Title	Off-Policy Policy Gradient with State Distribution Correction
Authors	Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill
Abstract	We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what would be the distribution of states under the learned policy. Here we build on recent progress for estimating the ratio of the state distributions under behavior and evaluation policies for policy evaluation, and present an off-policy policy gradient optimization technique that can account for this mismatch in distributions. We present an illustrative example of why this is important and a theoretical convergence guarantee for our approach. Empirically, we compare our method in simulations to several strong baselines which do not correct for this mismatch, significantly improving in the quality of the policy discovered.
Tasks
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08473v2
PDF	https://arxiv.org/pdf/1904.08473v2.pdf
PWC	https://paperswithcode.com/paper/off-policy-policy-gradient-with-state
Repo
Framework

SGD momentum optimizer with step estimation by online parabola model


Title	SGD momentum optimizer with step estimation by online parabola model
Authors	Jarek Duda
Abstract	In stochastic gradient descent, especially for neural network training, there are currently dominating first order methods: not modeling local distance to minimum. This information required for optimal step size is provided by second order methods, however, they have many difficulties, starting with full Hessian having square of dimension number of coefficients. This article proposes a minimal step from successful first order momentum method toward second order: online parabola modelling in just a single direction: normalized $\hat{v}$ from momentum method. It is done by estimating linear trend of gradients $\vec{g}=\nabla F(\vec{\theta})$ in $\hat{v}$ direction: such that $g(\vec{\theta}\bot+\theta\hat{v})\approx \lambda (\theta -p)$ for $\theta = \vec{\theta}\cdot \hat{v}$, $g= \vec{g}\cdot \hat{v}$, $\vec{\theta}\bot=\vec{\theta}-\theta\hat{v}$. Using linear regression, $\lambda$, $p$ are MSE estimated by just updating four averages (of $g$, $\theta$, $g\theta$, $\theta^2$) in the considered direction. Exponential moving averages allow here for inexpensive online estimation, weakening contribution of the old gradients. Controlling sign of curvature $\lambda$, we can repel from saddles in contrast to attraction in standard Newton method. In the remaining directions: not considered in second order model, we can simultaneously perform e.g. gradient descent. There is also discussed its learning rate approximation as $\mu=\sigma_\theta / \sigma_g$, allowing e.g. for adaptive SGD - with learning rate separately optimized (2nd order) for each parameter.
Tasks
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07063v3
PDF	https://arxiv.org/pdf/1907.07063v3.pdf
PWC	https://paperswithcode.com/paper/sgd-momentum-optimizer-with-step-estimation
Repo
Framework

Bifidelity data-assisted neural networks in nonintrusive reduced-order modeling


Title	Bifidelity data-assisted neural networks in nonintrusive reduced-order modeling
Authors	Chuan Lu, Xueyu Zhu
Abstract	In this paper, we present a new nonintrusive reduced basis method when a cheap low-fidelity model and expensive high-fidelity model are available. The method relies on proper orthogonal decomposition (POD) to generate the high-fidelity reduced basis and a shallow multilayer perceptron to learn the high-fidelity reduced coefficients. In contrast to other methods, one distinct feature of the proposed method is to incorporate the features extracted from the low-fidelity data as the input feature, this approach not only improves the predictive capability of the neural network but also enables the decoupling the high-fidelity simulation from the online stage. Due to its nonintrusive nature, it is applicable to general parameterized problems. We also provide several numerical examples to illustrate the effectiveness and performance of the proposed method.
Tasks
Published	2019-02-01
URL	http://arxiv.org/abs/1902.00148v2
PDF	http://arxiv.org/pdf/1902.00148v2.pdf
PWC	https://paperswithcode.com/paper/bifidelity-data-assisted-neural-networks-in
Repo
Framework