Paper Group ANR 471
Containment of Simple Regular Path Queries. Kernel Selection for Modal Linear Regression: Optimal Kernel and IRLS Algorithm. UnMask: Adversarial Detection and Defense Through Robust Feature Alignment. PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction. UPR: A Model-Driven Architecture for Deep Phase Retrieval. Residual T …
Containment of Simple Regular Path Queries
| Title | Containment of Simple Regular Path Queries |
| Authors | Diego Figueira, Adwait Godbole, S. Krishna, Wim Martens, Matthias Niewerth, Tina Trautner |
| Abstract | Testing containment of queries is a fundamental reasoning task in knowledge representation. We study here the containment problem for Conjunctive Regular Path Queries (CRPQs), a navigational query language extensively used in ontology and graph database querying. While it is known that containment of CRPQs is expspace-complete in general, we focus here on severely restricted fragments, which are known to be highly relevant in practice according to several recent studies. We obtain a detailed overview of the complexity of the containment problem, depending on the features used in the regular expressions of the queries, with completeness results for np, pitwo, pspace or expspace. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04411v1 |
| https://arxiv.org/pdf/2003.04411v1.pdf | |
| PWC | https://paperswithcode.com/paper/containment-of-simple-regular-path-queries |
| Repo | |
| Framework | |
Kernel Selection for Modal Linear Regression: Optimal Kernel and IRLS Algorithm
| Title | Kernel Selection for Modal Linear Regression: Optimal Kernel and IRLS Algorithm |
| Authors | Ryoya Yamasaki, Toshiyuki Tanaka |
| Abstract | Modal linear regression (MLR) is a method for obtaining a conditional mode predictor as a linear model. We study kernel selection for MLR from two perspectives: “which kernel achieves smaller error?” and “which kernel is computationally efficient?". First, we show that a Biweight kernel is optimal in the sense of minimizing an asymptotic mean squared error of a resulting MLR parameter. This result is derived from our refined analysis of an asymptotic statistical behavior of MLR. Secondly, we provide a kernel class for which iteratively reweighted least-squares algorithm (IRLS) is guaranteed to converge, and especially prove that IRLS with an Epanechnikov kernel terminates in a finite number of iterations. Simulation studies empirically verified that using a Biweight kernel provides good estimation accuracy and that using an Epanechnikov kernel is computationally efficient. Our results improve MLR of which existing studies often stick to a Gaussian kernel and modal EM algorithm specialized for it, by providing guidelines of kernel selection. |
| Tasks | |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11168v1 |
| https://arxiv.org/pdf/2001.11168v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-selection-for-modal-linear-regression |
| Repo | |
| Framework | |
UnMask: Adversarial Detection and Defense Through Robust Feature Alignment
| Title | UnMask: Adversarial Detection and Defense Through Robust Feature Alignment |
| Authors | Scott Freitas, Shang-Tse Chen, Zijie Wang, Duen Horng Chau |
| Abstract | Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are vulnerable to adversarial attacks–highlighting the vital need for defensive techniques to detect and mitigate these attacks before they occur. To combat these adversarial attacks, we developed UnMask, an adversarial detection and defense framework based on robust feature alignment. The core idea behind UnMask is to protect these models by verifying that an image’s predicted class (“bird”) contains the expected robust features (e.g., beak, wings, eyes). For example, if an image is classified as “bird”, but the extracted features are wheel, saddle and frame, the model may be under attack. UnMask detects such attacks and defends the model by rectifying the misclassification, re-classifying the image based on its robust features. Our extensive evaluation shows that UnMask (1) detects up to 96.75% of attacks, with a false positive rate of 9.66% and (2) defends the model by correctly classifying up to 93% of adversarial images produced by the current strongest attack, Projected Gradient Descent, in the gray-box setting. UnMask provides significantly better protection than adversarial training across 8 attack vectors, averaging 31.18% higher accuracy. Our proposed method is architecture agnostic and fast. We open source the code repository and data with this paper: https://github.com/unmaskd/unmask. |
| Tasks | Medical Diagnosis, Self-Driving Cars |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09576v1 |
| https://arxiv.org/pdf/2002.09576v1.pdf | |
| PWC | https://paperswithcode.com/paper/unmask-adversarial-detection-and-defense |
| Repo | |
| Framework | |
PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction
| Title | PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction |
| Authors | Meng Chen, Xiaohui Yu, Yang Liu |
| Abstract | Traffic problems have seriously affected people’s life quality and urban development, and forecasting the short-term traffic congestion is of great importance to both individuals and governments. However, understanding and modeling the traffic conditions can be extremely difficult, and our observations from real traffic data reveal that (1) similar traffic congestion patterns exist in the neighboring time slots and on consecutive workdays; (2) the levels of traffic congestion have clear multiscale properties. To capture these characteristics, we propose a novel method named PCNN based on deep Convolutional Neural Network, modeling Periodic traffic data for short-term traffic congestion prediction. PCNN has two pivotal procedures: time series folding and multi-grained learning. It first temporally folds the time series and constructs a two-dimensional matrix as the network input, such that both the real-time traffic conditions and past traffic patterns are well considered; then with a series of convolutions over the input matrix, it is able to model the local temporal dependency and multiscale traffic patterns. In particular, the global trend of congestion can be addressed at the macroscale; whereas more details and variations of the congestion can be captured at the microscale. Experimental results on a real-world urban traffic dataset confirm that folding time series data into a two-dimensional matrix is effective and PCNN outperforms the baselines significantly for the task of short-term congestion prediction. |
| Tasks | Time Series |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07033v1 |
| https://arxiv.org/pdf/2003.07033v1.pdf | |
| PWC | https://paperswithcode.com/paper/pcnn-deep-convolutional-networks-for-short |
| Repo | |
| Framework | |
UPR: A Model-Driven Architecture for Deep Phase Retrieval
| Title | UPR: A Model-Driven Architecture for Deep Phase Retrieval |
| Authors | Naveed Naimipour, Shahin Khobahi, Mojtaba Soltanalian |
| Abstract | The problem of phase retrieval has been intriguing researchers for decades due to its appearance in a wide range of applications. The task of a phase retrieval algorithm is typically to recover a signal from linear phase-less measurements. In this paper, we approach the problem by proposing a hybrid model-based data-driven deep architecture, referred to as the Unfolded Phase Retrieval (UPR), that shows potential in improving the performance of the state-of-the-art phase retrieval algorithms. Specifically, the proposed method benefits from versatility and interpretability of well established model-based algorithms, while simultaneously benefiting from the expressive power of deep neural networks. Our numerical results illustrate the effectiveness of such hybrid deep architectures and showcase the untapped potential of data-aided methodologies to enhance the existing phase retrieval algorithms. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04396v1 |
| https://arxiv.org/pdf/2003.04396v1.pdf | |
| PWC | https://paperswithcode.com/paper/upr-a-model-driven-architecture-for-deep |
| Repo | |
| Framework | |
Residual Tangent Kernels
| Title | Residual Tangent Kernels |
| Authors | Etai Littwin, Lior Wolf |
| Abstract | A recent body of work has focused on the theoretical study of neural networks at the regime of large width. Specifically, it was shown that training infinitely-wide and properly scaled vanilla ReLU networks using the L2 loss, is equivalent to kernel regression using the Neural Tangent Kernel (NTK), which is deterministic, and remains constant during training. In this work, we derive the form of the limiting kernel for architectures incorporating bypass connections, namely residual networks (ResNets), as well as to densely connected networks (DenseNets). In addition, we derive finite width and depth corrections for both cases. Our analysis reveals that deep practical residual architectures might operate much closer to the ``kernel regime’’ than their vanilla counterparts: while in networks that do not use skip connections, convergence to the NTK requires one to fix depth, while increasing the layers’ width. Our findings show that in ResNets, convergence to the NTK may occur when depth and width simultaneously tend to infinity, provided proper initialization. In DenseNets, however, convergence to the NTK as the width tend to infinity is guaranteed, at a rate that is independent of both depth and scale of the weights. | |
| Tasks | |
| Published | 2020-01-28 |
| URL | https://arxiv.org/abs/2001.10460v3 |
| https://arxiv.org/pdf/2001.10460v3.pdf | |
| PWC | https://paperswithcode.com/paper/residual-tangent-kernels |
| Repo | |
| Framework | |
An algorithm for reconstruction of triangle-free linear dynamic networks with verification of correctness
| Title | An algorithm for reconstruction of triangle-free linear dynamic networks with verification of correctness |
| Authors | Mihaela Dimovska, Donatello Materassi |
| Abstract | Reconstructing a network of dynamic systems from observational data is an active area of research. Many approaches guarantee a consistent reconstruction under the relatively strong assumption that the network dynamics is governed by strictly causal transfer functions. However, in many practical scenarios, strictly causal models are not adequate to describe the system and it is necessary to consider models with dynamics that include direct feedthrough terms. In presence of direct feedthroughs, guaranteeing a consistent reconstruction is a more challenging task. Indeed, under no additional assumptions on the network, we prove that, even in the limit of infinite data, any reconstruction method is susceptible to inferring edges that do not exist in the true network (false positives) or not detecting edges that are present in the network (false negative). However, for a class of triangle-free networks introduced in this article, some consistency guarantees can be provided. We present a method that either exactly recovers the topology of a triangle-free network certifying its correctness or outputs a graph that is sparser than the topology of the actual network, specifying that such a graph has no false positives, but there are false negatives. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02870v1 |
| https://arxiv.org/pdf/2003.02870v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-algorithm-for-reconstruction-of-triangle |
| Repo | |
| Framework | |
BARD: A structured technique for group elicitation of Bayesian networks to support analytic reasoning
| Title | BARD: A structured technique for group elicitation of Bayesian networks to support analytic reasoning |
| Authors | Ann E. Nicholson, Kevin B. Korb, Erik P. Nyberg, Michael Wybrow, Ingrid Zukerman, Steven Mascaro, Shreshth Thakur, Abraham Oshni Alvandi, Jeff Riley, Ross Pearson, Shane Morris, Matthieu Herrmann, A. K. M. Azad, Fergus Bolger, Ulrike Hahn, David Lagnado |
| Abstract | In many complex, real-world situations, problem solving and decision making require effective reasoning about causation and uncertainty. However, human reasoning in these cases is prone to confusion and error. Bayesian networks (BNs) are an artificial intelligence technology that models uncertain situations, supporting probabilistic and causal reasoning and decision making. However, to date, BN methodologies and software require significant upfront training, do not provide much guidance on the model building process, and do not support collaboratively building BNs. BARD (Bayesian ARgumentation via Delphi) is both a methodology and an expert system that utilises (1) BNs as the underlying structured representations for better argument analysis, (2) a multi-user web-based software platform and Delphi-style social processes to assist with collaboration, and (3) short, high-quality e-courses on demand, a highly structured process to guide BN construction, and a variety of helpful tools to assist in building and reasoning with BNs, including an automated explanation tool to assist effective report writing. The result is an end-to-end online platform, with associated online training, for groups without prior BN expertise to understand and analyse a problem, build a model of its underlying probabilistic causal structure, validate and reason with the causal model, and use it to produce a written analytic report. Initial experimental results demonstrate that BARD aids in problem solving, reasoning and collaboration. |
| Tasks | Decision Making |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.01207v1 |
| https://arxiv.org/pdf/2003.01207v1.pdf | |
| PWC | https://paperswithcode.com/paper/bard-a-structured-technique-for-group |
| Repo | |
| Framework | |
Unsupervised Latent Space Translation Network
| Title | Unsupervised Latent Space Translation Network |
| Authors | Magda Friedjungová, Daniel Vašata, Tomáš Chobola, Marcel Jiřina |
| Abstract | One task that is often discussed in a computer vision is the mapping of an image from one domain to a corresponding image in another domain known as image-to-image translation. Currently there are several approaches solving this task. In this paper, we present an enhancement of the UNIT framework that aids in removing its main drawbacks. More specifically, we introduce an additional adversarial discriminator on the latent representation used instead of VAE, which enforces the latent space distributions of both domains to be similar. On MNIST and USPS domain adaptation tasks, this approach greatly outperforms competing approaches. |
| Tasks | Domain Adaptation, Image-to-Image Translation |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09149v1 |
| https://arxiv.org/pdf/2003.09149v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-latent-space-translation-network |
| Repo | |
| Framework | |
Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
| Title | Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification |
| Authors | Devesh Walawalkar, Zhiqiang Shen, Zechun Liu, Marios Savvides |
| Abstract | Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional dropout strategies have been proposed, such as Cutout, DropBlock, CutMix, etc. These methods aim to promote the network to generalize better by partially occluding the discriminative parts of objects. However, all of them perform this operation randomly, without capturing the most important region(s) within an object. In this paper, we propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix. In each training iteration, we choose the most descriptive regions based on the intermediate attention maps from a feature extractor, which enables searching for the most discriminative parts in an image. Our proposed method is simple yet effective, easy to implement and can boost the baseline significantly. Extensive experiments on CIFAR-10/100, ImageNet datasets with various CNN architectures (in a unified setting) demonstrate the effectiveness of our proposed method, which consistently outperforms the baseline CutMix and other methods by a significant margin. |
| Tasks | Data Augmentation, Image Classification |
| Published | 2020-03-29 |
| URL | https://arxiv.org/abs/2003.13048v1 |
| https://arxiv.org/pdf/2003.13048v1.pdf | |
| PWC | https://paperswithcode.com/paper/attentive-cutmix-an-enhanced-data |
| Repo | |
| Framework | |
Optimal anytime regret with two experts
| Title | Optimal anytime regret with two experts |
| Authors | Nicholas J. A. Harvey, Christopher Liaw, Edwin Perkins, Sikander Randhawa |
| Abstract | The multiplicative weights method is an algorithm for the problem of prediction with expert advice. It achieves the minimax regret asymptotically if the number of experts is large, and the time horizon is known in advance. Optimal algorithms are also known if there are exactly two or three experts, and the time horizon is known in advance. In the anytime setting, where the time horizon is not known in advance, algorithms can be obtained by the doubling trick, but they are not optimal, let alone practical. No minimax optimal algorithm was previously known in the anytime setting, regardless of the number of experts. We design the first minimax optimal algorithm for minimizing regret in the anytime setting. We consider the case of two experts, and prove that the optimal regret is $\gamma \sqrt{t} / 2$ at all time steps $t$, where $\gamma$ is a natural constant that arose 35 years ago in studying fundamental properties of Brownian motion. The algorithm is designed by considering a continuous analogue, which is solved using ideas from stochastic calculus. |
| Tasks | |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08994v1 |
| https://arxiv.org/pdf/2002.08994v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-anytime-regret-with-two-experts |
| Repo | |
| Framework | |
Mixed Reinforcement Learning with Additive Stochastic Uncertainty
| Title | Mixed Reinforcement Learning with Additive Stochastic Uncertainty |
| Authors | Yao Mu, Shengbo Eben Li, Chang Liu, Qi Sun, Bingbing Nie, Bo Cheng, Baiyu Peng |
| Abstract | Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using dual representations of environmental dynamics to search the optimal policy with the purpose of improving both learning accuracy and training speed. The dual representations indicate the environmental model and the state-action data: the former can accelerate the learning process of RL, while its inherent model uncertainty generally leads to worse policy accuracy than the latter, which comes from direct measurements of states and actions. In the framework design of the mixed RL, the compensation of the additive stochastic model uncertainty is embedded inside the policy iteration RL framework by using explored state-action data via iterative Bayesian estimator (IBE). The optimal policy is then computed in an iterative way by alternating between policy evaluation (PEV) and policy improvement (PIM). The convergence of the mixed RL is proved using the Bellman’s principle of optimality, and the recursive stability of the generated policy is proved via the Lyapunov’s direct method. The effectiveness of the mixed RL is demonstrated by a typical optimal control problem of stochastic non-affine nonlinear systems (i.e., double lane change task with an automated vehicle). |
| Tasks | |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2003.00848v1 |
| https://arxiv.org/pdf/2003.00848v1.pdf | |
| PWC | https://paperswithcode.com/paper/mixed-reinforcement-learning-with-additive |
| Repo | |
| Framework | |
Safe Predictors for Enforcing Input-Output Specifications
| Title | Safe Predictors for Enforcing Input-Output Specifications |
| Authors | Stephen Mell, Olivia Brown, Justin Goodwin, Sung-Hyun Son |
| Abstract | We present an approach for designing correct-by-construction neural networks (and other machine learning models) that are guaranteed to be consistent with a collection of input-output specifications before, during, and after algorithm training. Our method involves designing a constrained predictor for each set of compatible constraints, and combining them safely via a convex combination of their predictions. We demonstrate our approach on synthetic datasets and an aircraft collision avoidance problem. |
| Tasks | |
| Published | 2020-01-29 |
| URL | https://arxiv.org/abs/2001.11062v1 |
| https://arxiv.org/pdf/2001.11062v1.pdf | |
| PWC | https://paperswithcode.com/paper/safe-predictors-for-enforcing-input-output |
| Repo | |
| Framework | |
SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images
| Title | SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images |
| Authors | Gideon Billings, Matthew Johnson-Roberson |
| Abstract | There has been much recent interest in deep learning methods for monocular image based object pose estimation. While object pose estimation is an important problem for autonomous robot interaction with the physical world, and the application space for monocular-based methods is expansive, there has been little work on applying these methods with fisheye imaging systems. Also, little exists in the way of annotated fisheye image datasets on which these methods can be developed and tested. The research landscape is even more sparse for object detection methods applied in the underwater domain, fisheye image based or otherwise. In this work, we present a novel framework for adapting a ROI-based 6D object pose estimation method to work on full fisheye images. The method incorporates the gnomic projection of regions of interest from an intermediate spherical image representation to correct for the fisheye distortions. Further, we contribute a fisheye image dataset, called UWHandles, collected in natural underwater environments, with 6D object pose and 2D bounding box annotations. |
| Tasks | 6D Pose Estimation using RGB, Object Detection, Pose Estimation |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12415v1 |
| https://arxiv.org/pdf/2002.12415v1.pdf | |
| PWC | https://paperswithcode.com/paper/silhonet-fisheye-adaptation-of-a-roi-based |
| Repo | |
| Framework | |
A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators
| Title | A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators |
| Authors | Caner Sahin, Guillermo Garcia-Hernando, Juil Sock, Tae-Kyun Kim |
| Abstract | Object pose recovery has gained increasing attention in the computer vision field as it has become an important problem in rapidly evolving technological areas related to autonomous driving, robotics, and augmented reality. Existing review-related studies have addressed the problem at visual level in 2D, going through the methods which produce 2D bounding boxes of objects of interest in RGB images. The 2D search space is enlarged either using the geometry information available in the 3D space along with RGB (Mono/Stereo) images, or utilizing depth data from LIDAR sensors and/or RGB-D cameras. 3D bounding box detectors, producing category-level amodal 3D bounding boxes, are evaluated on gravity aligned images, while full 6D object pose estimators are mostly tested at instance-level on the images where the alignment constraint is removed. Recently, 6D object pose estimation is tackled at the level of categories. In this paper, we present the first comprehensive and most recent review of the methods on object pose recovery, from 3D bounding box detectors to full 6D pose estimators. The methods mathematically model the problem as a classification, regression, classification & regression, template matching, and point-pair feature matching task. Based on this, a mathematical-model-based categorization of the methods is established. Datasets used for evaluating the methods are investigated with respect to the challenges, and evaluation metrics are studied. Quantitative results of experiments in the literature are analysed to show which category of methods best performs across what types of challenges. The analyses are further extended comparing two methods, which are our own implementations, so that the outcomes from the public results are further solidified. Current position of the field is summarized regarding object pose recovery, and possible research directions are identified. |
| Tasks | 6D Pose Estimation using RGB, Autonomous Driving, Pose Estimation |
| Published | 2020-01-28 |
| URL | https://arxiv.org/abs/2001.10609v1 |
| https://arxiv.org/pdf/2001.10609v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-on-object-pose-recovery-from-3d |
| Repo | |
| Framework | |
