April 1, 2020

3382 words 16 mins read

Paper Group ANR 436

Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives. Reinforcement Learning in Economics and Finance. Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach. SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances. A …

Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives


Title	Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives
Authors	Darvin Yi, Endre Grøvik, Michael Iv, Elizabeth Tong, Greg Zaharchuk, Daniel Rubin
Abstract	Deep learning has proven to be an essential tool for medical image analysis. However, the need for accurately labeled input data, often requiring time- and labor-intensive annotation by experts, is a major limitation to the use of deep learning. One solution to this challenge is to allow for use of coarse or noisy labels, which could permit more efficient and scalable labeling of images. In this work, we develop a lopsided loss function based on entropy regularization that assumes the existence of a nontrivial false negative rate in the target annotations. Starting with a carefully annotated brain metastasis lesion dataset, we simulate data with false negatives by (1) randomly censoring the annotated lesions and (2) systematically censoring the smallest lesions. The latter better models true physician error because smaller lesions are harder to notice than the larger ones. Even with a simulated false negative rate as high as 50%, applying our loss function to randomly censored data preserves maximum sensitivity at 97% of the baseline with uncensored training data, compared to just 10% for a standard loss function. For the size-based censorship, performance is restored from 17% with the current standard to 88% with our lopsided bootstrap loss. Our work will enable more efficient scaling of the image labeling process, in parallel with other approaches on creating more efficient user interfaces and tools for annotation.
Tasks
Published	2020-01-26
URL	https://arxiv.org/abs/2001.09501v1
PDF	https://arxiv.org/pdf/2001.09501v1.pdf
PWC	https://paperswithcode.com/paper/brain-metastasis-segmentation-network-trained
Repo
Framework

Reinforcement Learning in Economics and Finance


Title	Reinforcement Learning in Economics and Finance
Authors	Arthur Charpentier, Romuald Elie, Carl Remlinger
Abstract	Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal rewards. As in online learning, the agent learns sequentially. As in multi-armed bandit problems, when an agent picks an action, he can not infer ex-post the rewards induced by other action choices. In reinforcement learning, his actions have consequences: they influence not only rewards, but also future states of the world. The goal of reinforcement learning is to find an optimal policy – a mapping from the states of the world to the set of actions, in order to maximize cumulative reward, which is a long term strategy. Exploring might be sub-optimal on a short-term horizon but could lead to optimal long-term ones. Many problems of optimal control, popular in economics for more than forty years, can be expressed in the reinforcement learning framework, and recent advances in computational science, provided in particular by deep learning algorithms, can be used by economists in order to solve complex behavioral problems. In this article, we propose a state-of-the-art of reinforcement learning techniques, and present applications in economics, game theory, operation research and finance.
Tasks
Published	2020-03-22
URL	https://arxiv.org/abs/2003.10014v1
PDF	https://arxiv.org/pdf/2003.10014v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-in-economics-and
Repo
Framework

Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach


Title	Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach
Authors	Subin Huh, Insoon Yang
Abstract	Emerging applications in robotics and autonomous systems, such as autonomous driving and robotic surgery, often involve critical safety constraints that must be satisfied even when information about system models is limited. In this regard, we propose a model-free safety specification method that learns the maximal probability of safe operation by carefully combining probabilistic reachability analysis and safe reinforcement learning (RL). Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage. As a result, it yields a sequence of safe policies that determine the range of safe operation, called the safe set, which monotonically expands and gradually converges. We also develop an efficient safe exploration scheme that accelerates the process of identifying the safety of unexamined states. Exploiting the Lyapunov shielding, our method regulates the exploratory policy to avoid dangerous states with high confidence. To handle high-dimensional systems, we further extend our approach to deep RL by introducing a Lagrangian relaxation technique to establish a tractable actor-critic algorithm. The empirical performance of our method is demonstrated through continuous control benchmark problems, such as a reaching task on a planar robot arm.
Tasks	Autonomous Driving, Continuous Control, Safe Exploration
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10126v1
PDF	https://arxiv.org/pdf/2002.10126v1.pdf
PWC	https://paperswithcode.com/paper/safe-reinforcement-learning-for-probabilistic
Repo
Framework

SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances


Title	SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances
Authors	Yancheng Pan, Biao Gao, Jilin Mei, Sibo Geng, Chengkun Li, Huijing Zhao
Abstract	3D semantic segmentation is one of the key tasks for autonomous driving system. Recently, deep learning models for 3D semantic segmentation task have been widely researched, but they usually require large amounts of training data. However, the present datasets for 3D semantic segmentation are lack of point-wise annotation, diversiform scenes and dynamic objects. In this paper, we propose the SemanticPOSS dataset, which contains 2988 various and complicated LiDAR scans with large quantity of dynamic instances. The data is collected in Peking University and uses the same data format as SemanticKITTI. In addition, we evaluate several typical 3D semantic segmentation models on our SemanticPOSS dataset. Experimental results show that SemanticPOSS can help to improve the prediction accuracy of dynamic objects as people, car in some degree. SemanticPOSS will be published at \url{www.poss.pku.edu.cn}.
Tasks	3D Semantic Segmentation, Autonomous Driving, Semantic Segmentation
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09147v1
PDF	https://arxiv.org/pdf/2002.09147v1.pdf
PWC	https://paperswithcode.com/paper/semanticposs-a-point-cloud-dataset-with-large
Repo
Framework

A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions


Title	A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions
Authors	Amit Kumar Mondal
Abstract	Reinforcement learning is one of the core components in designing an artificial intelligent system emphasizing real-time response. Reinforcement learning influences the system to take actions within an arbitrary environment either having previous knowledge about the environment model or not. In this paper, we present a comprehensive study on Reinforcement Learning focusing on various dimensions including challenges, the recent development of different state-of-the-art techniques, and future directions. The fundamental objective of this paper is to provide a framework for the presentation of available methods of reinforcement learning that is informative enough and simple to follow for the new researchers and academics in this domain considering the latest concerns. First, we illustrated the core techniques of reinforcement learning in an easily understandable and comparable way. Finally, we analyzed and depicted the recent developments in reinforcement learning approaches. My analysis pointed out that most of the models focused on tuning policy values rather than tuning other things in a particular state of reasoning.
Tasks
Published	2020-01-19
URL	https://arxiv.org/abs/2001.06921v2
PDF	https://arxiv.org/pdf/2001.06921v2.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-reinforcement-learning-techniques
Repo
Framework

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction


Title	Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
Authors	Bingbin Liu, Ehsan Adeli, Zhangjie Cao, Kuan-Hui Lee, Abhijeet Shenoi, Adrien Gaidon, Juan Carlos Niebles
Abstract	Reasoning over visual data is a desirable capability for robotics and vision-based applications. Such reasoning enables forecasting of the next events or actions in videos. In recent years, various models have been developed based on convolution operations for prediction or forecasting, but they lack the ability to reason over spatiotemporal data and infer the relationships of different objects in the scene. In this paper, we present a framework based on graph convolution to uncover the spatiotemporal relationships in the scene for reasoning about pedestrian intent. A scene graph is built on top of segmented object instances within and across video frames. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is a very crucial piece of information for autonomous vehicles to navigate safely and more smoothly. We approach the problem of intent prediction from two different perspectives and anticipate the intention-to-cross within both pedestrian-centric and location-centric scenarios. In addition, we introduce a new dataset designed specifically for autonomous-driving scenarios in areas with dense pedestrian populations: the Stanford-TRI Intent Prediction (STIP) dataset. Our experiments on STIP and another benchmark dataset show that our graph modeling framework is able to predict the intention-to-cross of the pedestrians with an accuracy of 79.10% on STIP and 79.28% on \rev{Joint Attention for Autonomous Driving (JAAD) dataset up to one second earlier than when the actual crossing happens. These results outperform the baseline and previous work. Please refer to http://stip.stanford.edu/ for the dataset and code.
Tasks	Autonomous Driving, Autonomous Vehicles
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08945v1
PDF	https://arxiv.org/pdf/2002.08945v1.pdf
PWC	https://paperswithcode.com/paper/spatiotemporal-relationship-reasoning-for
Repo
Framework

Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic


Title	Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic
Authors	Yangang Ren, Jingliang Duan, Yang Guan, Shengbo Eben Li
Abstract	Reinforcement learning (RL) has achieved remarkable performance in a variety of sequential decision making and control tasks. However, a common problem is that learned nearly optimal policy always overfits to the training environment and may not be extended to situations never encountered during training. For practical applications, the randomness of the environment usually leads to rare but devastating events, which should be the focus of safety-critical systems, such as autonomous driving. In this paper, we introduce the minimax formulation and distributional framework to improve the generalization ability of RL algorithms and develop the Minimax Distributional Soft Actor-Critic (Minimax DSAC) algorithm. Minimax formulation aims to seek optimal policy considering the most serious disturbances from environment, in which the protagonist policy maximizes action-value function while the adversary policy tries to minimize it. Distributional framework aims to learn a state-action return distribution, from which we can model the risk of different returns explicitly, thus, formulating a risk-averse protagonist policy and a risk-seeking adversarial policy. We implement our method on the decision-making tasks of autonomous vehicles at intersections and test the trained policy in distinct environments from training environment. Results demonstrate that our method can greatly improve the generalization ability of the protagonist agent to different environmental variations.
Tasks	Autonomous Driving, Autonomous Vehicles, Decision Making
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05502v1
PDF	https://arxiv.org/pdf/2002.05502v1.pdf
PWC	https://paperswithcode.com/paper/improving-generalization-of-reinforcement
Repo
Framework

Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net


Title	Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net
Authors	Michal Byra, Piotr Jarosik, Katarzyna Dobruch-Sobczak, Ziemowit Klimonda, Hanna Piotrzkowska-Wroblewska, Jerzy Litniewski, Andrzej Nowicki
Abstract	We propose a novel deep learning based approach to breast mass segmentation in ultrasound (US) imaging. In comparison to commonly applied segmentation methods, which use US images, our approach is based on quantitative entropy parametric maps. To segment the breast masses we utilized an attention gated U-Net convolutional neural network. US images and entropy maps were generated based on raw US signals collected from 269 breast masses. The segmentation networks were developed separately using US image and entropy maps, and evaluated on a test set of 81 breast masses. The attention U-Net trained based on entropy maps achieved average Dice score of 0.60 (median 0.71), while for the model trained using US images we obtained average Dice score of 0.53 (median 0.59). Our work presents the feasibility of using quantitative US parametric maps for the breast mass segmentation. The obtained results suggest that US parametric maps, which provide the information about local tissue scattering properties, might be more suitable for the development of breast mass segmentation methods than regular US images.
Tasks
Published	2020-01-27
URL	https://arxiv.org/abs/2001.10061v1
PDF	https://arxiv.org/pdf/2001.10061v1.pdf
PWC	https://paperswithcode.com/paper/breast-mass-segmentation-based-on-ultrasonic
Repo
Framework

SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud


Title	SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud
Authors	Hongwei Yi, Shaoshuai Shi, Mingyu Ding, Jiankai Sun, Kui Xu, Hui Zhou, Zhe Wang, Sheng Li, Guoping Wang
Abstract	3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context information in LiDAR is seldom explored in previous works, which may help identify ambiguous vehicles. Second, the distribution of point cloud on vehicles varies continuously with increasing depths, which may not be well modeled by a single model. In this work, we propose a unified model SegVoxelNet to address the above two problems. A semantic context encoder is proposed to leverage the free-of-charge semantic segmentation masks in the bird’s eye view. Suspicious regions could be highlighted while noisy regions are suppressed by this module. To better deal with vehicles at different depths, a novel depth-aware head is designed to explicitly model the distribution differences and each part of the depth-aware head is made to focus on its own target detection range. Extensive experiments on the KITTI dataset show that the proposed method outperforms the state-of-the-art alternatives in both accuracy and efficiency with point cloud as input only.
Tasks	Autonomous Driving, Semantic Segmentation
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05316v1
PDF	https://arxiv.org/pdf/2002.05316v1.pdf
PWC	https://paperswithcode.com/paper/segvoxelnet-exploring-semantic-context-and
Repo
Framework

Multi-Modality Cascaded Fusion Technology for Autonomous Driving


Title	Multi-Modality Cascaded Fusion Technology for Autonomous Driving
Authors	Hongwu Kuang, Xiaodong Liu, Jingwei Zhang, Zicheng Fang
Abstract	Multi-modality fusion is the guarantee of the stability of autonomous driving systems. In this paper, we propose a general multi-modality cascaded fusion framework, exploiting the advantages of decision-level and feature-level fusion, utilizing target position, size, velocity, appearance and confidence to achieve accurate fusion results. In the fusion process, dynamic coordinate alignment(DCA) is conducted to reduce the error between sensors from different modalities. In addition, the calculation of affinity matrix is the core module of sensor fusion, we propose an affinity loss that improves the performance of deep affinity network(DAN). Last, the proposed step-by-step cascaded fusion framework is more interpretable and flexible compared to the end-toend fusion methods. Extensive experiments on Nuscenes [2] dataset show that our approach achieves the state-of-theart performance.dataset show that our approach achieves the state-of-the-art performance.
Tasks	Autonomous Driving, Sensor Fusion
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03138v1
PDF	https://arxiv.org/pdf/2002.03138v1.pdf
PWC	https://paperswithcode.com/paper/multi-modality-cascaded-fusion-technology-for
Repo
Framework

Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning


Title	Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning
Authors	Fei Ye, Xuxin Cheng, Pin Wang, Ching-Yao Chan
Abstract	Lane-change maneuvers are commonly executed by drivers to follow a certain routing plan, overtake a slower vehicle, adapt to a merging lane ahead, etc. However, improper lane change behaviors can be a major cause of traffic flow disruptions and even crashes. While many rule-based methods have been proposed to solve lane change problems for autonomous driving, they tend to exhibit limited performance due to the uncertainty and complexity of the driving environment. Machine learning-based methods offer an alternative approach, as Deep reinforcement learning (DRL) has shown promising success in many application domains including robotic manipulation, navigation, and playing video games. However, applying DRL for autonomous driving still faces many practical challenges in terms of slow learning rates, sample inefficiency, and non-stationary trajectories. In this study, we propose an automated lane change strategy using proximal policy optimization-based deep reinforcement learning, which shows great advantage in learning efficiency while maintaining stable performance. The trained agent is able to learn a smooth, safe, and efficient driving policy to determine lane-change decisions (i.e. when and how) even in dense traffic scenarios. The effectiveness of the proposed policy is validated using task success rate and collision rate, which demonstrates the lane change maneuvers can be efficiently learned and executed in a safe, smooth and efficient manner.
Tasks	Autonomous Driving
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02667v1
PDF	https://arxiv.org/pdf/2002.02667v1.pdf
PWC	https://paperswithcode.com/paper/automated-lane-change-strategy-using-proximal
Repo
Framework

Approximate Weighted First-Order Model Counting: Exploiting Fast Approximate Model Counters and Symmetry


Title	Approximate Weighted First-Order Model Counting: Exploiting Fast Approximate Model Counters and Symmetry
Authors	Timothy van Bremen, Ondrej Kuzelka
Abstract	We study the symmetric weighted first-order model counting task and present ApproxWFOMC, a novel anytime method for efficiently bounding the weighted first-order model count in the presence of an unweighted first-order model counting oracle. The algorithm has applications to inference in a variety of first-order probabilistic representations, such as Markov logic networks and probabilistic logic programs. Crucially for many applications, we make no assumptions on the form of the input sentence. Instead, our algorithm makes use of the symmetry inherent in the problem by imposing cardinality constraints on the number of possible true groundings of a sentence’s literals. Realising the first-order model counting oracle in practice using the approximate hashing-based model counter ApproxMC3, we show how our algorithm outperforms existing approximate and exact techniques for inference in first-order probabilistic models. We additionally provide PAC guarantees on the generated bounds.
Tasks
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05263v1
PDF	https://arxiv.org/pdf/2001.05263v1.pdf
PWC	https://paperswithcode.com/paper/approximate-weighted-first-order-model
Repo
Framework

Design Multimedia Expert Diagnosing Diseases System Using Fuzzy Logic (MEDDSFL)


Title	Design Multimedia Expert Diagnosing Diseases System Using Fuzzy Logic (MEDDSFL)
Authors	Mohammed Salah Ibrahim, Doaa Waleed Al-Dulaimee
Abstract	In this paper we designed an efficient expert system to diagnose diseases for human beings. The system depended on several clinical features for different diseases which will be used as knowledge base for this system. We used fuzzy logic system which is one of the most expert systems techniques that used in building knowledge base of expert systems. Fuzzy logic will be used to inference the results of disease diagnosing. We also provided the system with multimedia such as videos, pictures and information for most of disease that have been achieved in our system. The system implemented using Matlab ToolBox and fifteen diseases were studied. Five cases for normal, affected and unaffected people’s different diseases have been tested on this system. The results show that system was able to predict the status whether a human has a disease or not accurately. All system results are reported in tables and discussed in detail.
Tasks
Published	2020-03-22
URL	https://arxiv.org/abs/2003.09963v1
PDF	https://arxiv.org/pdf/2003.09963v1.pdf
PWC	https://paperswithcode.com/paper/design-multimedia-expert-diagnosing-diseases
Repo
Framework

GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks


Title	GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
Authors	Qiang Huang, Makoto Yamada, Yuan Tian, Dinesh Singh, Dawei Yin, Yi Chang
Abstract	Graph structured data has wide applicability in various domains such as physics, chemistry, biology, computer vision, and social networks, to name a few. Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. GNN is a deep learning based method that learns a node representation by combining specific nodes and the structural/topological information of a graph. However, like other deep models, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. More specifically, to explain a node, we generate a nonlinear interpretable model from its $N$-hop neighborhood and then compute the K most representative features as the explanations of its prediction using HSIC Lasso. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.
Tasks	Feature Selection
Published	2020-01-17
URL	https://arxiv.org/abs/2001.06216v1
PDF	https://arxiv.org/pdf/2001.06216v1.pdf
PWC	https://paperswithcode.com/paper/graphlime-local-interpretable-model
Repo
Framework

Efficient Algorithms for Multidimensional Segmented Regression


Title	Efficient Algorithms for Multidimensional Segmented Regression
Authors	Ilias Diakonikolas, Jerry Li, Anastasia Voloshinov
Abstract	We study the fundamental problem of fixed design {\em multidimensional segmented regression}: Given noisy samples from a function $f$, promised to be piecewise linear on an unknown set of $k$ rectangles, we want to recover $f$ up to a desired accuracy in mean-squared error. We provide the first sample and computationally efficient algorithm for this problem in any fixed dimension. Our algorithm relies on a simple iterative merging approach, which is novel in the multidimensional setting. Our experimental evaluation on both synthetic and real datasets shows that our algorithm is competitive and in some cases outperforms state-of-the-art heuristics. Code of our implementation is available at \url{https://github.com/avoloshinov/multidimensional-segmented-regression}.
Tasks
Published	2020-03-24
URL	https://arxiv.org/abs/2003.11086v1
PDF	https://arxiv.org/pdf/2003.11086v1.pdf
PWC	https://paperswithcode.com/paper/efficient-algorithms-for-multidimensional
Repo
Framework