Paper Group ANR 384
The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning. Substation Signal Matching with a Bagged Token Classifier. Detecting British Columbia Coastal Rainfall Patterns by Clustering Gaussian Processes. The Complexity of Limited Belief Reasoning – The Quantifier-Free Case. Deep Network Uncertainty Maps for In …
The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning
Title | The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning |
Authors | Vahid Behzadan, Arslan Munir |
Abstract | Since the inception of Deep Reinforcement Learning (DRL) algorithms, there has been a growing interest in both research and industrial communities in the promising potentials of this paradigm. The list of current and envisioned applications of deep RL ranges from autonomous navigation and robotics to control applications in the critical infrastructure, air traffic control, defense technologies, and cybersecurity. While the landscape of opportunities and the advantages of deep RL algorithms are justifiably vast, the security risks and issues in such algorithms remain largely unexplored. To facilitate and motivate further research on these critical challenges, this paper presents a foundational treatment of the security problem in DRL. We formulate the security requirements of DRL, and provide a high-level threat model through the classification and identification of vulnerabilities, attack vectors, and adversarial capabilities. Furthermore, we present a review of current literature on security of deep RL from both offensive and defensive perspectives. Lastly, we enumerate critical research venues and open problems in mitigation and prevention of intentional attacks against deep RL as a roadmap for further research in this area. |
Tasks | Autonomous Navigation |
Published | 2018-10-23 |
URL | http://arxiv.org/abs/1810.10369v1 |
http://arxiv.org/pdf/1810.10369v1.pdf | |
PWC | https://paperswithcode.com/paper/the-faults-in-our-pi-stars-security-issues |
Repo | |
Framework | |
Substation Signal Matching with a Bagged Token Classifier
Title | Substation Signal Matching with a Bagged Token Classifier |
Authors | Qin Wang, Sandro Schoenborn, Yvonne-Anne Pignolet, Theo Widmer, Carsten Franke |
Abstract | Currently, engineers at substation service providers match customer data with the corresponding internally used signal names manually. This paper proposes a machine learning method to automate this process based on substation signal mapping data from a repository of executed projects. To this end, a bagged token classifier is proposed, letting words (tokens) in the customer signal name vote for provider signal names. In our evaluation, the proposed method exhibits better performance in terms of both accuracy and efficiency over standard classifiers. |
Tasks | |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04734v1 |
http://arxiv.org/pdf/1802.04734v1.pdf | |
PWC | https://paperswithcode.com/paper/substation-signal-matching-with-a-bagged |
Repo | |
Framework | |
Detecting British Columbia Coastal Rainfall Patterns by Clustering Gaussian Processes
Title | Detecting British Columbia Coastal Rainfall Patterns by Clustering Gaussian Processes |
Authors | Forrest Paton, Paul D. McNicholas |
Abstract | Functional data analysis is a statistical framework where data are assumed to follow some functional form. This method of analysis is commonly applied to time series data, where time, measured continuously or in discrete intervals, serves as the location for a function’s value. Gaussian processes are a generalization of the multivariate normal distribution to function space and, in this paper, they are used to shed light on coastal rainfall patterns in British Columbia (BC). Specifically, this work addressed the question over how one should carry out an exploratory cluster analysis for the BC, or any similar, coastal rainfall data. An approach is developed for clustering multiple processes observed on a comparable interval, based on how similar their underlying covariance kernel is. This approach provides significant insights into the BC data, and these insights can be described in terms of El Nino and La Nina; however, the result is not simply one cluster representing El Nino years and another for La Nina years. From one perspective, the results show that clustering annual rainfall can potentially be used to identify extreme weather patterns. |
Tasks | Gaussian Processes, Time Series |
Published | 2018-12-23 |
URL | http://arxiv.org/abs/1812.09758v1 |
http://arxiv.org/pdf/1812.09758v1.pdf | |
PWC | https://paperswithcode.com/paper/detecting-british-columbia-coastal-rainfall |
Repo | |
Framework | |
The Complexity of Limited Belief Reasoning – The Quantifier-Free Case
Title | The Complexity of Limited Belief Reasoning – The Quantifier-Free Case |
Authors | Yijia Chen, Abdallah Saffidine, Christoph Schwering |
Abstract | The classical view of epistemic logic is that an agent knows all the logical consequences of their knowledge base. This assumption of logical omniscience is often unrealistic and makes reasoning computationally intractable. One approach to avoid logical omniscience is to limit reasoning to a certain belief level, which intuitively measures the reasoning “depth.” This paper investigates the computational complexity of reasoning with belief levels. First we show that while reasoning remains tractable if the level is constant, the complexity jumps to PSPACE-complete – that is, beyond classical reasoning – when the belief level is part of the input. Then we further refine the picture using parameterized complexity theory to investigate how the belief level and the number of non-logical symbols affect the complexity. |
Tasks | |
Published | 2018-05-08 |
URL | http://arxiv.org/abs/1805.02912v1 |
http://arxiv.org/pdf/1805.02912v1.pdf | |
PWC | https://paperswithcode.com/paper/the-complexity-of-limited-belief-reasoning |
Repo | |
Framework | |
Deep Network Uncertainty Maps for Indoor Navigation
Title | Deep Network Uncertainty Maps for Indoor Navigation |
Authors | Francesco Verdoja, Jens Lundell, Ville Kyrki |
Abstract | Most mobile robots for indoor use rely on 2D laser scanners for localization, mapping and navigation. These sensors, however, cannot detect transparent surfaces or measure the full occupancy of complex objects such as tables. Deep Neural Networks have recently been proposed to overcome this limitation by learning to estimate object occupancy. These estimates are nevertheless subject to uncertainty, making the evaluation of their confidence an important issue for these measures to be useful for autonomous navigation and mapping. In this work we approach the problem from two sides. First we discuss uncertainty estimation in deep models, proposing a solution based on a fully convolutional neural network. The proposed architecture is not restricted by the assumption that the uncertainty follows a Gaussian model, as in the case of many popular solutions for deep model uncertainty estimation, such as Monte-Carlo Dropout. We present results showing that uncertainty over obstacle distances is actually better modeled with a Laplace distribution. Then, we propose a novel approach to build maps based on Deep Neural Network uncertainty models. In particular, we present an algorithm to build a map that includes information over obstacle distance estimates while taking into account the level of uncertainty in each estimate. We show how the constructed map can be used to increase global navigation safety by planning trajectories which avoid areas of high uncertainty, enabling higher autonomy for mobile robots in indoor settings. |
Tasks | Autonomous Navigation |
Published | 2018-09-13 |
URL | https://arxiv.org/abs/1809.04891v3 |
https://arxiv.org/pdf/1809.04891v3.pdf | |
PWC | https://paperswithcode.com/paper/deep-network-uncertainty-maps-for-indoor |
Repo | |
Framework | |
Extracting textual overlays from social media videos using neural networks
Title | Extracting textual overlays from social media videos using neural networks |
Authors | Adam Słucki, Tomasz Trzcinski, Adam Bielski, Paweł Cyrta |
Abstract | Textual overlays are often used in social media videos as people who watch them without the sound would otherwise miss essential information conveyed in the audio stream. This is why extraction of those overlays can serve as an important meta-data source, e.g. for content classification or retrieval tasks. In this work, we present a robust method for extracting textual overlays from videos that builds up on multiple neural network architectures. The proposed solution relies on several processing steps: keyframe extraction, text detection and text recognition. The main component of our system, i.e. the text recognition module, is inspired by a convolutional recurrent neural network architecture and we improve its performance using synthetically generated dataset of over 600,000 images with text prepared by authors specifically for this task. We also develop a filtering method that reduces the amount of overlapping text phrases using Levenshtein distance and further boosts system’s performance. The final accuracy of our solution reaches over 80A% and is au pair with state-of-the-art methods. |
Tasks | |
Published | 2018-04-27 |
URL | http://arxiv.org/abs/1804.10687v2 |
http://arxiv.org/pdf/1804.10687v2.pdf | |
PWC | https://paperswithcode.com/paper/extracting-textual-overlays-from-social-media |
Repo | |
Framework | |
Histological images segmentation of mucous glands
Title | Histological images segmentation of mucous glands |
Authors | A. Khvostikov, A. Krylov, O. Kharlova, N. Oleynikova, I. Mikhailov, P. Malkov |
Abstract | Mucous glands lesions analysis and assessing of malignant potential of colon polyps are very important tasks of surgical pathology. However, differential diagnosis of colon polyps often seems impossible by classical methods and it is necessary to involve computer methods capable of assessing minimal differences to extend the capabilities of the classical pathology examination. Accurate segmentation of mucous glands from histology images is a crucial step to obtain reliable morphometric criteria for quantitative diagnostic methods. We review major trends in histological images segmentation and design a new convolutional neural network for mucous gland segmentation. |
Tasks | |
Published | 2018-06-20 |
URL | http://arxiv.org/abs/1806.07781v1 |
http://arxiv.org/pdf/1806.07781v1.pdf | |
PWC | https://paperswithcode.com/paper/histological-images-segmentation-of-mucous |
Repo | |
Framework | |
Technical Report: Inconsistency in Answer Set Programs and Extensions
Title | Technical Report: Inconsistency in Answer Set Programs and Extensions |
Authors | Christoph Redl |
Abstract | Answer Set Programming (ASP) is a well-known problem solving approach based on nonmonotonic logic programs. HEX-programs extend ASP with external atoms for accessing arbitrary external information, which can introduce values that do not appear in the input program. In this work we consider inconsistent ASP- and HEX-programs, i.e., programs without answer sets. We study characterizations of inconsistency, introduce a novel notion for explaining inconsistencies in terms of input facts, analyze the complexity of reasoning tasks in context of inconsistency analysis, and present techniques for computing inconsistency reasons. This theoretical work is motivated by two concrete applications, which we also present. The first one is the new modeling technique of query answering over subprograms as a convenient alternative to the well-known saturation technique. The second application is a new evaluation algorithm for HEX-programs based on conflict-driven learning for programs with multiple components: while for certain program classes previous techniques suffer an evaluation bottleneck, the new approach shows significant, potentially exponential speedup in our experiments. Since well-known ASP extensions such as constraint ASP and DL-programs correspond to special cases of HEX, all presented results are interesting beyond the specific formalism. |
Tasks | |
Published | 2018-05-31 |
URL | http://arxiv.org/abs/1806.00119v1 |
http://arxiv.org/pdf/1806.00119v1.pdf | |
PWC | https://paperswithcode.com/paper/technical-report-inconsistency-in-answer-set |
Repo | |
Framework | |
Alternating Linear Bandits for Online Matrix-Factorization Recommendation
Title | Alternating Linear Bandits for Online Matrix-Factorization Recommendation |
Authors | Hamid Dadkhahi, Sahand Negahban |
Abstract | We consider the problem of online collaborative filtering in the online setting, where items are recommended to the users over time. At each time step, the user (selected by the environment) consumes an item (selected by the agent) and provides a rating of the selected item. In this paper, we propose a novel algorithm for online matrix factorization recommendation that combines linear bandits and alternating least squares. In this formulation, the bandit feedback is equal to the difference between the ratings of the best and selected items. We evaluate the performance of the proposed algorithm over time using both cumulative regret and average cumulative NDCG. Simulation results over three synthetic datasets as well as three real-world datasets for online collaborative filtering indicate the superior performance of the proposed algorithm over two state-of-the-art online algorithms. |
Tasks | |
Published | 2018-10-22 |
URL | http://arxiv.org/abs/1810.09401v1 |
http://arxiv.org/pdf/1810.09401v1.pdf | |
PWC | https://paperswithcode.com/paper/alternating-linear-bandits-for-online-matrix |
Repo | |
Framework | |
Efficient identification, localization and quantification of grapevine inflorescences in unprepared field images using Fully Convolutional Networks
Title | Efficient identification, localization and quantification of grapevine inflorescences in unprepared field images using Fully Convolutional Networks |
Authors | Robert Rudolph, Katja Herzog, Reinhard Töpfer, Volker Steinhage |
Abstract | Yield and its prediction is one of the most important tasks in grapevine breeding purposes and vineyard management. Commonly, this trait is estimated manually right before harvest by extrapolation, which mostly is labor-intensive, destructive and inaccurate. In the present study an automated image-based workflow was developed quantifying inflorescences and single flowers in unprepared field images of grapevines, i.e. no artificial background or light was applied. It is a novel approach for non-invasive, inexpensive and objective phenotyping with high-throughput. First, image regions depicting inflorescences were identified and localized. This was done by segmenting the images into the classes “inflorescence” and “non-inflorescence” using a Fully Convolutional Network (FCN). Efficient image segmentation hereby is the most challenging step regarding the small geometry and dense distribution of flowers (several hundred flowers per inflorescence), similar color of all plant organs in the fore- and background as well as the circumstance that only approximately 5% of an image show inflorescences. The trained FCN achieved a mean Intersection Over Union (IOU) of 87.6% on the test data set. Finally, individual flowers were extracted from the “inflorescence”-areas using Circular Hough Transform. The flower extraction achieved a recall of 80.3% and a precision of 70.7% using the segmentation derived by the trained FCN model. Summarized, the presented approach is a promising strategy in order to predict yield potential automatically in the earliest stage of grapevine development which is applicable for objective monitoring and evaluations of breeding material, genetic repositories or commercial vineyards. |
Tasks | Semantic Segmentation |
Published | 2018-07-10 |
URL | http://arxiv.org/abs/1807.03770v1 |
http://arxiv.org/pdf/1807.03770v1.pdf | |
PWC | https://paperswithcode.com/paper/efficient-identification-localization-and |
Repo | |
Framework | |
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
Title | Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator |
Authors | Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu |
Abstract | We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high probability guarantees of sub-linear regret on this problem. We further study the interplay between regret minimization and parameter estimation by proving a lower bound on the expected regret in terms of the exploration schedule used by any algorithm. Finally, we conduct a numerical study comparing our robust adaptive algorithm to other methods from the adaptive LQR literature, and demonstrate the flexibility of our proposed method by extending it to a demand forecasting problem subject to state constraints. |
Tasks | |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09388v1 |
http://arxiv.org/pdf/1805.09388v1.pdf | |
PWC | https://paperswithcode.com/paper/regret-bounds-for-robust-adaptive-control-of |
Repo | |
Framework | |
50 Years of Test (Un)fairness: Lessons for Machine Learning
Title | 50 Years of Test (Un)fairness: Lessons for Machine Learning |
Authors | Ben Hutchinson, Margaret Mitchell |
Abstract | Quantitative definitions of what is unfair and what is fair have been introduced in multiple disciplines for well over 50 years, including in education, hiring, and machine learning. We trace how the notion of fairness has been defined within the testing communities of education and hiring over the past half century, exploring the cultural and social context in which different fairness definitions have emerged. In some cases, earlier definitions of fairness are similar or identical to definitions of fairness in current machine learning research, and foreshadow current formal work. In other cases, insights into what fairness means and how to measure it have largely gone overlooked. We compare past and current notions of fairness along several dimensions, including the fairness criteria, the focus of the criteria (e.g., a test, a model, or its use), the relationship of fairness to individuals, groups, and subgroups, and the mathematical method for measuring fairness (e.g., classification, regression). This work points the way towards future research and measurement of (un)fairness that builds from our modern understanding of fairness while incorporating insights from the past. |
Tasks | |
Published | 2018-11-25 |
URL | http://arxiv.org/abs/1811.10104v2 |
http://arxiv.org/pdf/1811.10104v2.pdf | |
PWC | https://paperswithcode.com/paper/50-years-of-test-unfairness-lessons-for |
Repo | |
Framework | |
Scale Drift Correction of Camera Geo-Localization using Geo-Tagged Images
Title | Scale Drift Correction of Camera Geo-Localization using Geo-Tagged Images |
Authors | Kazuya Iwami, Satoshi Ikehata, Kiyoharu Aizawa |
Abstract | Camera geo-localization from a monocular video is a fundamental task for video analysis and autonomous navigation. Although 3D reconstruction is a key technique to obtain camera poses, monocular 3D reconstruction in a large environment tends to result in the accumulation of errors in rotation, translation, and especially in scale: a problem known as scale drift. To overcome these errors, we propose a novel framework that integrates incremental structure from motion (SfM) and a scale drift correction method utilizing geo-tagged images, such as those provided by Google Street View. Our correction method begins by obtaining sparse 6-DoF correspondences between the reconstructed 3D map coordinate system and the world coordinate system, by using geo-tagged images. Then, it corrects scale drift by applying pose graph optimization over Sim(3) constraints and bundle adjustment. Experimental evaluations on large-scale datasets show that the proposed framework not only sufficiently corrects scale drift, but also achieves accurate geo-localization in a kilometer-scale environment. |
Tasks | 3D Reconstruction, Autonomous Navigation |
Published | 2018-08-26 |
URL | http://arxiv.org/abs/1808.08544v1 |
http://arxiv.org/pdf/1808.08544v1.pdf | |
PWC | https://paperswithcode.com/paper/scale-drift-correction-of-camera-geo |
Repo | |
Framework | |
A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation
Title | A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation |
Authors | Guillermo Gallego, Henri Rebecq, Davide Scaramuzza |
Abstract | We present a unifying framework to solve several computer vision problems with event cameras: motion, depth and optical flow estimation. The main idea of our framework is to find the point trajectories on the image plane that are best aligned with the event data by maximizing an objective function: the contrast of an image of warped events. Our method implicitly handles data association between the events, and therefore, does not rely on additional appearance information about the scene. In addition to accurately recovering the motion parameters of the problem, our framework produces motion-corrected edge-like images with high dynamic range that can be used for further scene analysis. The proposed method is not only simple, but more importantly, it is, to the best of our knowledge, the first method that can be successfully applied to such a diverse set of important vision tasks with event cameras. |
Tasks | Optical Flow Estimation |
Published | 2018-04-04 |
URL | http://arxiv.org/abs/1804.01306v1 |
http://arxiv.org/pdf/1804.01306v1.pdf | |
PWC | https://paperswithcode.com/paper/a-unifying-contrast-maximization-framework |
Repo | |
Framework | |
A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation
Title | A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation |
Authors | Gabriel Sepulveda, Juan Carlos Niebles, Alvaro Soto |
Abstract | We present a semantically rich graph representation for indoor robotic navigation. Our graph representation encodes: semantic locations such as offices or corridors as nodes, and navigational behaviors such as enter office or cross a corridor as edges. In particular, our navigational behaviors operate directly from visual inputs to produce motor controls and are implemented with deep learning architectures. This enables the robot to avoid explicit computation of its precise location or the geometry of the environment, and enables navigation at a higher level of semantic abstraction. We evaluate the effectiveness of our representation by simulating navigation tasks in a large number of virtual environments. Our results show that using a simple sets of perceptual and navigational behaviors, the proposed approach can successfully guide the way of the robot as it completes navigational missions such as going to a specific office. Furthermore, our implementation shows to be effective to control the selection and switching of behaviors. |
Tasks | Autonomous Navigation |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04119v1 |
http://arxiv.org/pdf/1803.04119v1.pdf | |
PWC | https://paperswithcode.com/paper/a-deep-learning-based-behavioral-approach-to |
Repo | |
Framework | |