Paper Group ANR 761
Towards Accurate Camera Geopositioning by Image Matching. Cause Identification of Electromagnetic Transient Events using Spatiotemporal Feature Learning. Variance Estimation For Dynamic Regression via Spectrum Thresholding. Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images. Anomaly Detection with Adversarial Dual …
Towards Accurate Camera Geopositioning by Image Matching
| Title | Towards Accurate Camera Geopositioning by Image Matching |
| Authors | Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, Peter de With |
| Abstract | In this work, we present a camera geopositioning system based on matching a query image against a database with panoramic images. For matching, our system uses memory vectors aggregated from global image descriptors based on convolutional features to facilitate fast searching in the database. To speed up searching, a clustering algorithm is used to balance geographical positioning and computation time. We refine the obtained position from the query image using a new outlier removal algorithm. The matching of the query image is obtained with a recall@5 larger than 90% for panorama-to-panorama matching. We cluster available panoramas from geographically adjacent locations into a single compact representation and observe computational gains of approximately 50% at the cost of only a small (approximately 3%) recall loss. Finally, we present a coordinate estimation algorithm that reduces the median geopositioning error by up to 20%. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05454v1 |
| http://arxiv.org/pdf/1903.05454v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-accurate-camera-geopositioning-by |
| Repo | |
| Framework | |
Cause Identification of Electromagnetic Transient Events using Spatiotemporal Feature Learning
| Title | Cause Identification of Electromagnetic Transient Events using Spatiotemporal Feature Learning |
| Authors | Iman Niazazari, Reza Jalilzadeh Hamidi, Hanif Livani, Reza Arghandeh |
| Abstract | This paper presents a spatiotemporal unsupervised feature learning method for cause identification of electromagnetic transient events (EMTE) in power grids. The proposed method is formulated based on the availability of time-synchronized high-frequency measurement, and using the convolutional neural network (CNN) as the spatiotemporal feature representation along with softmax function. Despite the existing threshold-based, or energy-based events analysis methods, such as support vector machine (SVM), autoencoder, and tapered multi-layer perception (t-MLP) neural network, the proposed feature learning is carried out with respect to both time and space. The effectiveness of the proposed feature learning and the subsequent cause identification is validated through the EMTP simulation of different events such as line energization, capacitor bank energization, lightning, fault, and high-impedance fault in the IEEE 30-bus, and the real-time digital simulation (RTDS) of the WSCC 9-bus system. |
| Tasks | |
| Published | 2019-03-10 |
| URL | http://arxiv.org/abs/1903.04486v1 |
| http://arxiv.org/pdf/1903.04486v1.pdf | |
| PWC | https://paperswithcode.com/paper/cause-identification-of-electromagnetic |
| Repo | |
| Framework | |
Variance Estimation For Dynamic Regression via Spectrum Thresholding
| Title | Variance Estimation For Dynamic Regression via Spectrum Thresholding |
| Authors | Mark Kozdoba, Edward Moroshko, Shie Mannor, Koby Crammer |
| Abstract | We consider the dynamic linear regression problem, where the predictor vector may vary with time. This problem can be modeled as a linear dynamical system, where the parameters that need to be learned are the variance of both the process noise and the observation noise. While variance estimation for dynamic regression is a natural problem, with a variety of applications, existing approaches to this problem either lack guarantees or only have asymptotic guarantees without explicit rates. In addition, all existing approaches rely strongly on Guassianity of the noises. In this paper we study the global system operator: the operator that maps the noise vectors to the output. In particular, we obtain estimates on its spectrum, and as a result derive the first known variance estimators with finite sample complexity guarantees. Moreover, our results hold for arbitrary sub Gaussian distributions of noise terms. We evaluate the approach on synthetic and real-world benchmarks. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05591v3 |
| https://arxiv.org/pdf/1906.05591v3.pdf | |
| PWC | https://paperswithcode.com/paper/variance-estimation-for-online-regression-via |
| Repo | |
| Framework | |
Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images
| Title | Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images |
| Authors | Xinyi Huang, Suphanut Jamonnak, Ye Zhao, Boyu Wang, Minh Hoai, Kevin Yager, Wei Xu |
| Abstract | This extended abstract presents a visualization system, which is designed for domain scientists to visually understand their deep learning model of extracting multiple attributes in x-ray scattering images. The system focuses on studying the model behaviors related to multiple structural attributes. It allows users to explore the images in the feature space, the classification output of different attributes, with respect to the actual attributes labelled by domain scientists. Abundant interactions allow users to flexibly select instance images, their clusters, and compare them visually in details. Two preliminary case studies demonstrate its functionalities and usefulness. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04357v1 |
| https://arxiv.org/pdf/1910.04357v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-understanding-of-multiple-attributes |
| Repo | |
| Framework | |
Anomaly Detection with Adversarial Dual Autoencoders
| Title | Anomaly Detection with Adversarial Dual Autoencoders |
| Authors | Ha Son Vu, Daisuke Ueta, Kiyoshi Hashimoto, Kazuki Maeno, Sugiri Pranata, Sheng Mei Shen |
| Abstract | Semi-supervised and unsupervised Generative Adversarial Networks (GAN)-based methods have been gaining popularity in anomaly detection task recently. However, GAN training is somewhat challenging and unstable. Inspired from previous work in GAN-based image generation, we introduce a GAN-based anomaly detection framework - Adversarial Dual Autoencoders (ADAE) - consists of two autoencoders as generator and discriminator to increase training stability. We also employ discriminator reconstruction error as anomaly score for better detection performance. Experiments across different datasets of varying complexity show strong evidence of a robust model that can be used in different scenarios, one of which is brain tumor detection. |
| Tasks | Anomaly Detection, Image Generation |
| Published | 2019-02-19 |
| URL | http://arxiv.org/abs/1902.06924v1 |
| http://arxiv.org/pdf/1902.06924v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-with-adversarial-dual |
| Repo | |
| Framework | |
Automated and Network Structure Preserving Segmentation of Optical Coherence Tomography Angiograms
| Title | Automated and Network Structure Preserving Segmentation of Optical Coherence Tomography Angiograms |
| Authors | Ylenia Giarratano, Eleonora Bianchi, Calum Gray, Andrew Morris, Tom MacGillivray, Baljean Dhillon, Miguel O. Bernabeu |
| Abstract | Optical coherence tomography angiography (OCTA) is a novel non-invasive imaging modality for the visualisation of microvasculature in vivo. OCTA has encountered broad adoption in retinal research. OCTA potential in the assessment of pathological conditions and the reproducibility of studies relies on the quality of the image analysis. However, automated segmentation of parafoveal OCTA images is still an open problem in the field. In this study, we generate the first open dataset of retinal parafoveal OCTA images with associated ground truth manual segmentations. Furthermore, we establish a standard for OCTA image segmentation by surveying a broad range of state-of-the-art vessel enhancement and binarisation procedures. We provide the most comprehensive comparison of these methods under a unified framework to date. Our results show that, for the set of images considered, the U-Net machine learning (ML) architecture achieves the best performance with a Dice similarity coefficient of 0.89. For applications where manually segmented data is not available to retrain this ML approach, our findings suggest that optimal oriented flux is the best handcrafted filter enhancement method for OCTA images from those considered. Furthermore, we report on the importance of preserving network connectivity in the segmentation to enable vascular network phenotyping. We introduce a new metric for network connectivity evaluations in segmented angiograms and report an accuracy of up to 0.94 in preserving the morphological structure of the network in our segmentations. Finally, we release our data and source code to support standardisation efforts in OCTA image segmentation. |
| Tasks | Semantic Segmentation |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09978v1 |
| https://arxiv.org/pdf/1912.09978v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-and-network-structure-preserving |
| Repo | |
| Framework | |
Learning low-dimensional dynamical-system models from noisy frequency-response data with Loewner rational interpolation
| Title | Learning low-dimensional dynamical-system models from noisy frequency-response data with Loewner rational interpolation |
| Authors | Zlatko Drmač, Benjamin Peherstorfer |
| Abstract | Loewner rational interpolation provides a versatile tool to learn low-dimensional dynamical-system models from frequency-response measurements. This work investigates the robustness of the Loewner approach to noise. The key finding is that if the measurements are polluted with Gaussian noise, then the error due to the noise grows at most linearly with the standard deviation with high probability under certain conditions. The analysis gives insights on how to make the Loewner approach robust against noise via linear transformations and judicious selections of measurements. Numerical results demonstrate the linear growth of the error on benchmark examples. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00110v1 |
| https://arxiv.org/pdf/1910.00110v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-low-dimensional-dynamical-system |
| Repo | |
| Framework | |
Harnessing the Power of Deep Learning Methods in Healthcare: Neonatal Pain Assessment from Crying Sound
| Title | Harnessing the Power of Deep Learning Methods in Healthcare: Neonatal Pain Assessment from Crying Sound |
| Authors | Md Sirajus Salekin, Ghada Zamzmi, Rahul Paul, Dmitry Goldgof, Rangachar Kasturi, Thao Ho, Yu Sun |
| Abstract | Neonatal pain assessment in clinical environments is challenging as it is discontinuous and biased. Facial/body occlusion can occur in such settings due to clinical condition, developmental delays, prone position, or other external factors. In such cases, crying sound can be used to effectively assess neonatal pain. In this paper, we investigate the use of a novel CNN architecture (N-CNN) along with other CNN architectures (VGG16 and ResNet50) for assessing pain from crying sounds of neonates. The experimental results demonstrate that using our novel N-CNN for assessing pain from the sounds of neonates has a strong clinical potential and provides a viable alternative to the current assessment practice. |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02543v1 |
| https://arxiv.org/pdf/1909.02543v1.pdf | |
| PWC | https://paperswithcode.com/paper/harnessing-the-power-of-deep-learning-methods |
| Repo | |
| Framework | |
Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning
| Title | Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning |
| Authors | Shumpei Kubosawa, Takashi Onishi, Yoshimasa Tsuruoka |
| Abstract | Chemical plants are complex and dynamical systems consisting of many components for manipulation and sensing, whose state transitions depend on various factors such as time, disturbance, and operation procedures. For the purpose of supporting human operators of chemical plants, we are developing an AI system that can semi-automatically synthesize operation procedures for efficient and stable operation. Our system can provide not only appropriate operation procedures but also reasons why the procedures are considered to be valid. This is achieved by integrating automated reasoning and deep reinforcement learning technologies with a chemical plant simulator and external knowledge. Our preliminary experimental results demonstrate that it can synthesize a procedure that achieves a much faster recovery from a malfunction compared to standard PID control. |
| Tasks | |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02183v1 |
| http://arxiv.org/pdf/1903.02183v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthesizing-chemical-plant-operation |
| Repo | |
| Framework | |
Bias-Variance Tradeoff in a Sliding Window Implementation of the Stochastic Gradient Algorithm
| Title | Bias-Variance Tradeoff in a Sliding Window Implementation of the Stochastic Gradient Algorithm |
| Authors | Yakup Ceki Papo |
| Abstract | This paper provides a framework to analyze stochastic gradient algorithms in a mean squared error (MSE) sense using the asymptotic normality result of the stochastic gradient descent (SGD) iterates. We perform this analysis by taking the asymptotic normality result and applying it to the finite iteration case. Specifically, we look at problems where the gradient estimators are biased and have reduced variance and compare the iterates generated by these gradient estimators to the iterates generated by the SGD algorithm. We use the work of Fabian to characterize the mean and the variance of the distribution of the iterates in terms of the bias and the covariance matrix of the gradient estimators. We introduce the sliding window SGD (SW-SGD) algorithm, with its proof of convergence, which incurs a lower MSE than the SGD algorithm on quadratic and convex problems. Lastly, we present some numerical results to show the effectiveness of this framework and the superiority of SW-SGD algorithm over the SGD algorithm. |
| Tasks | |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11868v1 |
| https://arxiv.org/pdf/1910.11868v1.pdf | |
| PWC | https://paperswithcode.com/paper/bias-variance-tradeoff-in-a-sliding-window |
| Repo | |
| Framework | |
Uncertainty Quantification in Ensembles of Honest Regression Trees using Generalized Fiducial Inference
| Title | Uncertainty Quantification in Ensembles of Honest Regression Trees using Generalized Fiducial Inference |
| Authors | Suofei Wu, Jan Hannig, Thomas C. M. Lee |
| Abstract | Due to their accuracies, methods based on ensembles of regression trees are a popular approach for making predictions. Some common examples include Bayesian additive regression trees, boosting and random forests. This paper focuses on honest random forests, which add honesty to the original form of random forests and are proved to have better statistical properties. The main contribution is a new method that quantifies the uncertainties of the estimates and predictions produced by honest random forests. The proposed method is based on the generalized fiducial methodology, and provides a fiducial density function that measures how likely each single honest tree is the true model. With such a density function, estimates and predictions, as well as their confidence/prediction intervals, can be obtained. The promising empirical properties of the proposed method are demonstrated by numerical comparisons with several state-of-the-art methods, and by applications to a few real data sets. Lastly, the proposed method is theoretically backed up by a strong asymptotic guarantee. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06177v1 |
| https://arxiv.org/pdf/1911.06177v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-quantification-in-ensembles-of |
| Repo | |
| Framework | |
Adversarial Patches Exploiting Contextual Reasoning in Object Detection
| Title | Adversarial Patches Exploiting Contextual Reasoning in Object Detection |
| Authors | Aniruddha Saha, Akshayvarun Subramanya, Koninika Patil, Hamed Pirsiavash |
| Abstract | The utilization of spatial context to improve accuracy in most fast object detection algorithms is well known. The detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning for their predictions. We show that an adversary can exploit such contextual reasoning to fool standard detectors. We develop adversarial patches that make an object detector blind to a particular category even though the patch does not overlap with the missed detections. We also study methods to fix this vulnerability and show that limiting the use of contextual reasoning during object detector training acts as a form of defense that makes the detector robust. We believe defending against context based adversarial attack algorithms is not easy. We take a step towards that direction and urge the research community to give attention to this vulnerability. |
| Tasks | Adversarial Attack, Object Detection, Real-Time Object Detection |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00068v2 |
| https://arxiv.org/pdf/1910.00068v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-patches-exploiting-contextual |
| Repo | |
| Framework | |
Confirmatory Factor Analysis – A Case study
| Title | Confirmatory Factor Analysis – A Case study |
| Authors | Rui Portocarrero Sarmento, Vera Costa |
| Abstract | Confirmatory Factor Analysis (CFA) is a particular form of factor analysis, most commonly used in social research. In confirmatory factor analysis, the researcher first develops a hypothesis about what factors they believe are underlying the used measures and may impose constraints on the model based on these a priori hypotheses. For example, if two factors are accounting for the covariance in the measures, and these factors are unrelated to one another, we can create a model where the correlation between factor X and factor Y is set to zero. Measures could then be obtained to assess how well the fitted model captured the covariance between all the items or measures in the model. Thus, if the results of statistical tests of the model fit indicate a poor fit, the model will be rejected. If the fit is weak, it may be due to a variety of reasons. We propose to introduce state of the art techniques to do CFA in R language. Then, we propose to do some examples of CFA with R and some datasets, revealing several scenarios where CFA is relevant. |
| Tasks | |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.05598v1 |
| https://arxiv.org/pdf/1905.05598v1.pdf | |
| PWC | https://paperswithcode.com/paper/190505598 |
| Repo | |
| Framework | |
Neural Language Modeling with Visual Features
| Title | Neural Language Modeling with Visual Features |
| Authors | Antonios Anastasopoulos, Shankar Kumar, Hank Liao |
| Abstract | Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our models on data that is two orders-of-magnitude bigger than datasets used in prior work. We perform a thorough exploration of model architectures for combining visual and text features. Our experiments on two corpora (YouCookII and 20bn-something-something-v2) show that the best performing architecture consists of middle fusion of visual and text features, yielding over 25% relative improvement in perplexity. We report analysis that provides insights into why our multimodal language model improves upon a standard RNN language model. |
| Tasks | Language Modelling |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.02930v1 |
| http://arxiv.org/pdf/1903.02930v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-language-modeling-with-visual-features |
| Repo | |
| Framework | |
F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds
| Title | F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds |
| Authors | Qi Chen |
| Abstract | Autonomous vehicles are heavily reliant upon their sensors to perfect the perception of surrounding environments, however, with the current state of technology, the data which a vehicle uses is confined to that from its own sensors. Data sharing between vehicles and/or edge servers is limited by the available network bandwidth and the stringent real-time constraints of autonomous driving applications. To address these issues, we propose a point cloud feature based cooperative perception framework (F-Cooper) for connected autonomous vehicles to achieve a better object detection precision. Not only will feature based data be sufficient for the training process, we also use the features’ intrinsically small size to achieve real-time edge computing, without running the risk of congesting the network. Our experiment results show that by fusing features, we are able to achieve a better object detection result, around 10% improvement for detection within 20 meters and 30% for further distances, as well as achieve faster edge computing with a low communication delay, requiring 71 milliseconds in certain feature selections. To the best of our knowledge, we are the first to introduce feature-level data fusion to connected autonomous vehicles for the purpose of enhancing object detection and making real-time edge computing on inter-vehicle data feasible for autonomous vehicles. |
| Tasks | Autonomous Driving, Autonomous Vehicles, Object Detection, Real-Time Object Detection |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06459v1 |
| https://arxiv.org/pdf/1909.06459v1.pdf | |
| PWC | https://paperswithcode.com/paper/f-cooper-feature-based-cooperative-perception |
| Repo | |
| Framework | |
