Paper Group ANR 50
Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks. End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances. Unsupervised Projection Networks for Generative Adversarial Networks. Generating Semantic Adversarial Examples with Differentiable Rendering …
Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
| Title | Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks |
| Authors | Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia, Felix Li, Rowan McAllister, Joseph E. Gonzalez, Sergey Levine, Francesco Borrelli, Ken Goldberg |
| Abstract | Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes it hard to enforce constraints during learning. We address these issues with a new model-based reinforcement learning algorithm, safety augmented value estimation from demonstrations (SAVED), which uses supervision that only identifies task completion and a modest set of suboptimal demonstrations to constrain exploration and learn efficiently while handling complex constraints. We derive iterative improvement guarantees for SAVED under known stochastic nonlinear systems. We then compare SAVED with 3 state-of-the-art model-based and model-free RL algorithms on 6 standard simulation benchmarks involving navigation and manipulation and 2 real-world tasks on the da Vinci surgical robot. Results suggest that SAVED outperforms prior methods in terms of success rate, constraint satisfaction, and sample efficiency, making it feasible to safely learn complex maneuvers directly on a real robot in less than an hour. For tasks on the robot, baselines succeed less than 5% of the time while SAVED has a success rate of over 75% in the first 50 training iterations. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13402v6 |
| https://arxiv.org/pdf/1905.13402v6.pdf | |
| PWC | https://paperswithcode.com/paper/extending-deep-model-predictive-control-with |
| Repo | |
| Framework | |
End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances
| Title | End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances |
| Authors | Marin Toromanoff, Emilie Wirbel, Fabien Moutarde |
| Abstract | Reinforcement Learning (RL) aims at learning an optimal behavior policy from its own experiments and not rule-based control methods. However, there is no RL algorithm yet capable of handling a task as difficult as urban driving. We present a novel technique, coined implicit affordances, to effectively leverage RL for urban driving thus including lane keeping, pedestrians and vehicles avoidance, and traffic light detection. To our knowledge we are the first to present a successful RL agent handling such a complex task especially regarding the traffic light detection. Furthermore, we have demonstrated the effectiveness of our method by winning the Camera Only track of the CARLA challenge. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10868v2 |
| https://arxiv.org/pdf/1911.10868v2.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-model-free-reinforcement-learning |
| Repo | |
| Framework | |
Unsupervised Projection Networks for Generative Adversarial Networks
| Title | Unsupervised Projection Networks for Generative Adversarial Networks |
| Authors | Daiyaan Arfeen, Jesse Zhang |
| Abstract | We propose the use of unsupervised learning to train projection networks that project onto the latent space of an already trained generator. We apply our method to a trained StyleGAN, and use our projection network to perform image super-resolution and clustering of images into semantically identifiable groups. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00579v2 |
| https://arxiv.org/pdf/1910.00579v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-projection-networks-for |
| Repo | |
| Framework | |
Generating Semantic Adversarial Examples with Differentiable Rendering
| Title | Generating Semantic Adversarial Examples with Differentiable Rendering |
| Authors | Lakshya Jain, Wilson Wu, Steven Chen, Uyeong Jang, Varun Chandrasekaran, Sanjit Seshia, Somesh Jha |
| Abstract | Machine learning (ML) algorithms, especially deep neural networks, have demonstrated success in several domains. However, several types of attacks have raised concerns about deploying ML in safety-critical domains, such as autonomous driving and security. An attacker perturbs a data point slightly in the concrete feature space (e.g., pixel space) and causes the ML algorithm to produce incorrect output (e.g. a perturbed stop sign is classified as a yield sign). These perturbed data points are called adversarial examples, and there are numerous algorithms in the literature for constructing adversarial examples and defending against them. In this paper we explore semantic adversarial examples (SAEs) where an attacker creates perturbations in the semantic space representing the environment that produces input for the ML model. For example, an attacker can change the background of the image to be cloudier to cause misclassification. We present an algorithm for constructing SAEs that uses recent advances in differential rendering and inverse graphics. |
| Tasks | Autonomous Driving |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.00727v1 |
| https://arxiv.org/pdf/1910.00727v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-semantic-adversarial-examples-with |
| Repo | |
| Framework | |
DRCAS: Deep Restoration Network for Hardware Based Compressive Acquisition Scheme
| Title | DRCAS: Deep Restoration Network for Hardware Based Compressive Acquisition Scheme |
| Authors | Pravir Singh Gupta, Xin Yuan, Gwan Seong Choi |
| Abstract | We investigate the power and performance improvement in image acquisition devices by the use of CAS (Compressed Acquisition Scheme) and DNN (Deep Neural Networks). Towards this end, we propose a novel image acquisition scheme HCAS (Hardware based Compressed Acquisition Scheme) using hardware-based binning (downsampling), bit truncation and JPEG compression and develop a deep learning based reconstruction network for images acquired using the same. HCAS is motivated by the fact that in-situ compression of raw data using binning and bit truncation results in reduction in data traffic and power in the entire downstream image processing pipeline and additional compression of processed data using JPEG will help in storage/transmission of images. The combination of in-situ compression with JPEG leads to high compression ratios, significant power savings with further advantages of image acquisition simplification. Bearing these concerns in mind, we propose DRCAS (Deep Restoration network for hardware based Compressed Acquisition Scheme), which to our best knowledge, is the first work proposed in the literature for restoration of images acquired using acquisition scheme like HCAS. When compared with the CAS methods (bicubic downsampling) used in super resolution tasks in literature, HCAS proposed in this paper performs superior in terms of both compression ratio and being hardware friendly. The restoration network DRCAS also perform superior than state-of-the-art super resolution networks while being much smaller. Thus HCAS and DRCAS technique will enable us to design much simpler and power efficient image acquisition pipelines. |
| Tasks | Image Restoration, Image Super-Resolution, Super-Resolution |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10136v2 |
| https://arxiv.org/pdf/1909.10136v2.pdf | |
| PWC | https://paperswithcode.com/paper/190910136 |
| Repo | |
| Framework | |
A Survey of Predictive Maintenance: Systems, Purposes and Approaches
| Title | A Survey of Predictive Maintenance: Systems, Purposes and Approaches |
| Authors | Yongyi Ran, Xin Zhou, Pengfeng Lin, Yonggang Wen, Ruilong Deng |
| Abstract | This paper provides a comprehensive literature review on Predictive Maintenance (PdM) with emphasis on system architectures, purposes and approaches. In industry, any outages and unplanned downtime of machines or systems would degrade or interrupt a company’s core business, potentially resulting in significant penalties and unmeasurable reputation loss. Existing traditional maintenance approaches suffer from some assumptions and limits, such as high prevent/repair costs, inadequate or inaccurate mathematical degradation processes and manual feature extraction. With the trend of smart manufacturing and development of Internet of Things (IoT), data mining and Artificial Intelligence (AI), etc., PdM is proposed as a novel type of maintenance paradigm to perform maintenances only after the analytical models predict certain failures or degradations. In this survey, we first provide a high-level view of the PdM system architectures including the Open System Architecture for Condition Based Monitoring (OSA-CBM), cloud-enhanced PdM system and PdM 4.0, etc. Then, we make clear the specific maintenance purposes/objectives, which mainly comprise cost minimization, availability/reliability maximization and multi-objective optimization. Furthermore, we provide a review of the existing approaches for fault diagnosis and prognosis in PdM systems that include three major subcategories: knowledge based, traditional Machine Learning (ML) based and DL based approaches. We make a brief review on the knowledge based and traditional ML based approaches applied in diverse industrial systems or components with a complete list of references, while providing a comprehensive review of DL based approaches. Finally, important future research directions are introduced. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.07383v1 |
| https://arxiv.org/pdf/1912.07383v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-predictive-maintenance-systems |
| Repo | |
| Framework | |
Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision
| Title | Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision |
| Authors | Yubao Liu, Kai Lin |
| Abstract | Although many methods have been proposed to deal with nature image super-resolution (SR) and get impressive performance, the text images SR is not good due to their ignorance of document images. In this paper, we propose a matting-based dual generative adversarial network (mdGAN) for document image SR. Firstly, the input image is decomposed into document text, foreground and background layers using deep image matting. Then two parallel branches are constructed to recover text boundary information and color information respectively. Furthermore, in order to improve the restoration accuracy of characters in output image, we use the input image’s corresponding ground truth text label as extra supervise information to refine the two-branch networks during training. Experiments on real text images demonstrate that our method outperforms several state-of-the-art methods quantitatively and qualitatively. |
| Tasks | Image Matting, Image Super-Resolution, Super-Resolution |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.12909v1 |
| https://arxiv.org/pdf/1909.12909v1.pdf | |
| PWC | https://paperswithcode.com/paper/deeply-matting-based-dual-generative |
| Repo | |
| Framework | |
Domain Adaptation for One-Class Classification: Monitoring the Health of Critical Systems Under Limited Information
| Title | Domain Adaptation for One-Class Classification: Monitoring the Health of Critical Systems Under Limited Information |
| Authors | Gabriel Michau, Olga Fink |
| Abstract | The failure of a complex and safety critical industrial asset can have extremely high consequences. Close monitoring for early detection of abnormal system conditions is therefore required. Data-driven solutions to this problem have been limited for two reasons: First, safety critical assets are designed and maintained to be highly reliable and faults are rare. Fault detection can thus not be solved with supervised learning. Second, complex industrial systems usually have long lifetime during which they face very different operating conditions. In the early life of the system, the collected data is probably not representative of future operating conditions, making it challenging to train a robust model. In this paper, we propose a methodology to monitor the systems in their early life. To do so, we enhance the training dataset with other units from a fleet, for which longer observations are available. Since each unit has its own specificity, we propose to extract features made independent of their origin by three unsupervised feature alignment techniques. First, using a variational encoder, we impose a shared probabilistic encoder/decoder for both units. Second, we introduce a new loss designed to conserve inter-point spacial relationships between the input and the learned features. Last, we propose to train in an adversarial manner a discriminator on the origin of the features. Once aligned, the features are fed to a one-class classifier to monitor the health of the system. By exploring the different combinations of the proposed alignment strategies, and by testing them on a real case study, a fleet composed of 112 power plants operated in different geographical locations and under very different operating regimes, we demonstrate that this alignment is necessary and beneficial. |
| Tasks | Domain Adaptation, Fault Detection, One-class classifier |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09204v2 |
| https://arxiv.org/pdf/1907.09204v2.pdf | |
| PWC | https://paperswithcode.com/paper/fully-unsupervised-feature-alignment-for |
| Repo | |
| Framework | |
Overcoming Forgetting in Federated Learning on Non-IID Data
| Title | Overcoming Forgetting in Federated Learning on Non-IID Data |
| Authors | Neta Shoham, Tomer Avidor, Aviv Keren, Nadav Israel, Daniel Benditkis, Liron Mor-Yosef, Itai Zeitak |
| Abstract | We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to converge to a shared optimum. We show that this can be done efficiently for communication (adding no further privacy risks), scaling with the number of nodes in the distributed setting. Our experiments show that this method is superior to competing ones for image recognition on the MNIST dataset. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.07796v1 |
| https://arxiv.org/pdf/1910.07796v1.pdf | |
| PWC | https://paperswithcode.com/paper/overcoming-forgetting-in-federated-learning |
| Repo | |
| Framework | |
Using Image Priors to Improve Scene Understanding
| Title | Using Image Priors to Improve Scene Understanding |
| Authors | Brigit Schroeder, Hanlin Tang, Alexandre Alahi |
| Abstract | Semantic segmentation algorithms that can robustly segment objects across multiple camera viewpoints are crucial for assuring navigation and safety in emerging applications such as autonomous driving. Existing algorithms treat each image in isolation, but autonomous vehicles often revisit the same locations or maintain information from the immediate past. We propose a simple yet effective method for leveraging these image priors to improve semantic segmentation of images from sequential driving datasets. We examine several methods to fuse these temporal scene priors, and introduce a prior fusion network that is able to learn how to transfer this information. The prior fusion model improves the accuracy over the non-prior baseline from 69.1% to 73.3% for dynamic classes, and from 88.2% to 89.1% for static classes. Compared to models such as FCN-8, our prior method achieves the same accuracy with 5 times fewer parameters. We used a simple encoder decoder backbone, but this general prior fusion method could be applied to more complex semantic segmentation backbones. We also discuss how structured representations of scenes in the form of a scene graph could be leveraged as priors to further improve scene understanding. |
| Tasks | Autonomous Driving, Autonomous Vehicles, Scene Understanding, Semantic Segmentation |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01198v1 |
| https://arxiv.org/pdf/1910.01198v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-image-priors-to-improve-scene |
| Repo | |
| Framework | |
Graph-Embedded Multi-layer Kernel Extreme Learning Machine for One-class Classification or (Graph-Embedded Multi-layer Kernel Ridge Regression for One-class Classification)
| Title | Graph-Embedded Multi-layer Kernel Extreme Learning Machine for One-class Classification or (Graph-Embedded Multi-layer Kernel Ridge Regression for One-class Classification) |
| Authors | Chandan Gautam, Aruna Tiwari, M. Tanveer |
| Abstract | A brain can detect outlier just by using only normal samples. Similarly, one-class classification (OCC) also uses only normal samples to train the model and trained model can be used for outlier detection. In this paper, a multi-layer architecture for OCC is proposed by stacking various Graph-Embedded Kernel Ridge Regression (KRR) based Auto-Encoders in a hierarchical fashion. These Auto-Encoders are formulated under two types of Graph-Embedding, namely, local and global variance-based embedding. This Graph-Embedding explores the relationship between samples and multi-layers of Auto-Encoder project the input features into new feature space. The last layer of this proposed architecture is Graph-Embedded regression-based one-class classifier. The Auto-Encoders use an unsupervised approach of learning and the final layer uses semi-supervised (trained by only positive samples and obtained closed-form solution) approach to learning. The proposed method is experimentally evaluated on 21 publicly available benchmark datasets. Experimental results verify the effectiveness of the proposed one-class classifiers over 11 existing state-of-the-art kernel-based one-class classifiers. Friedman test is also performed to verify the statistical significance of the claim of the superiority of the proposed one-class classifiers over the existing state-of-the-art methods. By using two types of Graph-Embedding, 4 variants of Graph-Embedded multi-layer KRR-based one-class classifier has been presented in this paper. All 4 variants performed better than the existing one-class classifiers in terms of various discussed criteria in this paper. Hence, it can be a viable alternative for OCC task. In the future, various other types of Auto-Encoders can be explored within proposed architecture. |
| Tasks | Graph Embedding, One-class classifier, Outlier Detection |
| Published | 2019-04-13 |
| URL | http://arxiv.org/abs/1904.06491v1 |
| http://arxiv.org/pdf/1904.06491v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-embedded-multi-layer-kernel-extreme |
| Repo | |
| Framework | |
Prescriptive Cluster-Dependent Support Vector Machines with an Application to Reducing Hospital Readmissions
| Title | Prescriptive Cluster-Dependent Support Vector Machines with an Application to Reducing Hospital Readmissions |
| Authors | Taiyao Wang, Ioannis Ch. Paschalidis |
| Abstract | We augment linear Support Vector Machine (SVM) classifiers by adding three important features: (i) we introduce a regularization constraint to induce a sparse classifier; (ii) we devise a method that partitions the positive class into clusters and selects a sparse SVM classifier for each cluster; and (iii) we develop a method to optimize the values of controllable variables in order to reduce the number of data points which are predicted to have an undesirable outcome, which, in our setting, coincides with being in the positive class. The latter feature leads to personalized prescriptions/recommendations. We apply our methods to the problem of predicting and preventing hospital readmissions within 30-days from discharge for patients that underwent a general surgical procedure. To that end, we leverage a large dataset containing over 2.28 million patients who had surgeries in the period 2011–2014 in the U.S. The dataset has been collected as part of the American College of Surgeons National Surgical Quality Improvement Program (NSQIP). |
| Tasks | |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09056v1 |
| http://arxiv.org/pdf/1903.09056v1.pdf | |
| PWC | https://paperswithcode.com/paper/prescriptive-cluster-dependent-support-vector |
| Repo | |
| Framework | |
De-Biasing The Lasso With Degrees-of-Freedom Adjustment
| Title | De-Biasing The Lasso With Degrees-of-Freedom Adjustment |
| Authors | Pierre C. Bellec, Cun-Hui Zhang |
| Abstract | This paper studies schemes to de-bias the Lasso in a linear model $y=X\beta+\epsilon$ where the goal is to construct confidence intervals for $a_0^T\beta$ in a direction $a_0$, where $X$ has iid $N(0,\Sigma)$ rows. We show that previously analyzed propositions to de-bias the Lasso require a modification in order to enjoy efficiency in a full range of sparsity. This modification takes the form of a degrees-of-freedom adjustment that accounts for the dimension of the model selected by Lasso. Let $s_0$ be the true sparsity. If $\Sigma$ is known and the ideal score vector proportional to $X\Sigma^{-1}a_0$ is used, the unadjusted de-biasing schemes proposed previously enjoy efficiency if $s_0\lll n^{2/3}$. However, if $s_0\ggg n^{2/3}$, the unadjusted schemes cannot be efficient in certain $a_0$: then it is necessary to modify existing procedures by a degrees-of-freedom adjustment. This modification grants asymptotic efficiency for any $a_0$ when $s_0/p\to 0$ and $s_0\log(p/s_0)/n \to 0$. If $\Sigma$ is unknown, efficiency is granted for general $a_0$ when $$\frac{s_0\log p}{n}+\min\Big{\frac{s_\Omega\log p}{n},\frac{\Sigma^{-1}a_0_1\sqrt{\log p}}{\Sigma^{-1/2}a_0_2 \sqrt n}\Big}+\frac{\min(s_\Omega,s_0)\log p}{\sqrt n}\to0$$ where $s_\Omega=\Sigma^{-1}a_0_0$, provided that the de-biased estimate is modified with the degrees-of-freedom adjustment. The dependence in $s_0,s_\Omega$ and $\Sigma^{-1}a_0_1$ is optimal. Our estimated score vector provides a novel methodology to handle dense $a_0$. Our analysis shows that the degrees-of-freedom adjustment is not needed when the initial bias in direction $a_0$ is small, which is granted under stringent conditions on $\Sigma^{-1}$. The main proof argument is an interpolation path similar to that typically used to derive Slepian’s lemma. It yields a new $\ell_\infty$ error bound for the Lasso which is of independent interest. |
| Tasks | |
| Published | 2019-02-24 |
| URL | https://arxiv.org/abs/1902.08885v2 |
| https://arxiv.org/pdf/1902.08885v2.pdf | |
| PWC | https://paperswithcode.com/paper/de-biasing-the-lasso-with-degrees-of-freedom |
| Repo | |
| Framework | |
AED-Net: An Abnormal Event Detection Network
| Title | AED-Net: An Abnormal Event Detection Network |
| Authors | Tian Wang, Zichen Miao, Yuxin Chen, Yi Zhou, Guangcun Shan, Hichem Snoussi |
| Abstract | It is challenging to detect the anomaly in crowded scenes for quite a long time. In this paper, a self-supervised framework, abnormal event detection network (AED-Net), which is composed of PCAnet and kernel principal component analysis (kPCA), is proposed to address this problem. Using surveillance video sequences of different scenes as raw data, PCAnet is trained to extract high-level semantics of crowd’s situation. Next, kPCA,a one-class classifier, is trained to determine anomaly of the scene. In contrast to some prevailing deep learning methods,the framework is completely self-supervised because it utilizes only video sequences in a normal situation. Experiments of global and local abnormal event detection are carried out on UMN and UCSD datasets, and competitive results with higher EER and AUC compared to other state-of-the-art methods are observed. Furthermore, by adding local response normalization (LRN) layer, we propose an improvement to original AED-Net. And it is proved to perform better by promoting the framework’s generalization capacity according to the experiments. |
| Tasks | One-class classifier |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.11891v1 |
| http://arxiv.org/pdf/1903.11891v1.pdf | |
| PWC | https://paperswithcode.com/paper/aed-net-an-abnormal-event-detection-network |
| Repo | |
| Framework | |
The Exact Equivalence of Independence Testing and Two-Sample Testing
| Title | The Exact Equivalence of Independence Testing and Two-Sample Testing |
| Authors | Cencheng Shen, Carey E. Priebe, Joshua T. Vogelstein |
| Abstract | Testing independence and testing equality of distributions are two tightly related statistical hypotheses. Several distance and kernel-based statistics are recently proposed to achieve universally consistent testing for either hypothesis. On the distance side, the distance correlation is proposed for independence testing, and the energy statistic is proposed for two-sample testing. On the kernel side, the Hilbert-Schmidt independence criterion is proposed for independence testing and the maximum mean discrepancy is proposed for two-sample testing. In this paper, we show that two-sample testing are special cases of independence testing via an auxiliary label vector, and prove that distance correlation is exactly equivalent to the energy statistic in terms of the population statistic, the sample statistic, and the testing p-value via permutation test. The equivalence can be further generalized to K-sample testing and extended to the kernel regime. As a consequence, it suffices to always use an independence statistic to test equality of distributions, which enables better interpretability of the test statistic and more efficient testing. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.08883v1 |
| https://arxiv.org/pdf/1910.08883v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-exact-equivalence-of-independence-testing |
| Repo | |
| Framework | |
