Paper Group ANR 81
Grounded and Controllable Image Completion by Incorporating Lexical Semantics. Iterative training of neural networks for intra prediction. On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds. Detecting Deficient Coverage in Colonoscopies. Autocamera Calibration for traffic surveillance cameras with wide angle lenses. Machine …
Grounded and Controllable Image Completion by Incorporating Lexical Semantics
| Title | Grounded and Controllable Image Completion by Incorporating Lexical Semantics |
| Authors | Shengyu Zhang, Tan Jiang, Qinghao Huang, Ziqi Tan, Zhou Zhao, Siliang Tang, Jin Yu, Hongxia Yang, Yi Yang, Fei Wu |
| Abstract | In this paper, we present an approach, namely Lexical Semantic Image Completion (LSIC), that may have potential applications in art, design, and heritage conservation, among several others. Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge. To permit both grounded and controllable completion process, we advocate generating results faithful to both visual and lexical semantic context, i.e., the description of leaving holes or blank regions in the image (e.g., hole description). One major challenge for LSIC comes from modeling and aligning the structure of visual-semantic context and translating across different modalities. We term this process as structure completion, which is realized by multi-grained reasoning blocks in our model. Another challenge relates to the unimodal biases, which occurs when the model generates plausible results without using the textual description. This can be true since the annotated captions for an image are often semantically equivalent in existing datasets, and thus there is only one paired text for a masked image in training. We devise an unsupervised unpaired-creation learning path besides the over-explored paired-reconstruction path, as well as a multi-stage training strategy to mitigate the insufficiency of labeled data. We conduct extensive quantitative and qualitative experiments as well as ablation studies, which reveal the efficacy of our proposed LSIC. |
| Tasks | |
| Published | 2020-02-29 |
| URL | https://arxiv.org/abs/2003.00303v1 |
| https://arxiv.org/pdf/2003.00303v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounded-and-controllable-image-completion-by |
| Repo | |
| Framework | |
Iterative training of neural networks for intra prediction
| Title | Iterative training of neural networks for intra prediction |
| Authors | Thierry Dumas, Franck Galpin, Philippe Bordes |
| Abstract | This paper presents an iterative training of neural networks for intra prediction in a block-based image and video codec. First, the neural networks are trained on blocks arising from the codec partitioning of images, each paired with its context. Then, iteratively, blocks are collected from the partitioning of images via the codec including the neural networks trained at the previous iteration, each paired with its context, and the neural networks are retrained on the new pairs. Thanks to this training, the neural networks can learn intra prediction functions that both stand out from those already in the initial codec and boost the codec in terms of rate-distortion. Moreover, the iterative process allows the design of training data cleansings essential for the neural network training. When the iteratively trained neural networks are put into H.265 (HM-16.15), -4.2% of mean dB-rate reduction is obtained, that is -1.8% above the state-of-the-art. By moving them into H.266 (VTM-5.0), the mean dB-rate reduction reaches -1.9%. |
| Tasks | |
| Published | 2020-03-15 |
| URL | https://arxiv.org/abs/2003.06812v1 |
| https://arxiv.org/pdf/2003.06812v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-training-of-neural-networks-for |
| Repo | |
| Framework | |
On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds
| Title | On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds |
| Authors | Henrik Forssell, Evgeny Kharlamov, Evgenij Thorstensen |
| Abstract | Data exchange heavily relies on the notion of incomplete database instances. Several semantics for such instances have been proposed and include open (OWA), closed (CWA), and open-closed (OCWA) world. For all these semantics important questions are: whether one incomplete instance semantically implies another; when two are semantically equivalent; and whether a smaller or smallest semantically equivalent instance exists. For OWA and CWA these questions are fully answered. For several variants of OCWA, however, they remain open. In this work we adress these questions for Closed Powerset semantics and the OCWA semantics of Libkin and Sirangelo, 2011. We define a new OCWA semantics, called OCWA*, in terms of homomorphic covers that subsumes both semantics, and characterize semantic implication and equivalence in terms of such covers. This characterization yields a guess-and-check algorithm to decide equivalence, and shows that the problem is NP-complete. For the minimization problem we show that for several common notions of minimality there is in general no unique minimal equivalent instance for Closed Powerset semantics, and consequently not for the more expressive OCWA* either. However, for Closed Powerset semantics we show that one can find, for any incomplete database, a unique finite set of its subinstances which are subinstances (up to renaming of nulls) of all instances semantically equivalent to the original incomplete one. We study properties of this set, and extend the analysis to OCWA*. |
| Tasks | |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.04757v1 |
| https://arxiv.org/pdf/2001.04757v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-equivalence-and-cores-for-incomplete |
| Repo | |
| Framework | |
Detecting Deficient Coverage in Colonoscopies
| Title | Detecting Deficient Coverage in Colonoscopies |
| Authors | Daniel Freedman, Yochai Blau, Liran Katzir, Amit Aides, Ilan Shimshoni, Danny Veikherman, Tomer Golany, Ariel Gordon, Greg Corrado, Yossi Matias, Ehud Rivlin |
| Abstract | Colonoscopy is the tool of choice for preventing Colorectal Cancer, by detecting and removing polyps before they become cancerous. However, colonoscopy is hampered by the fact that endoscopists routinely miss 22-28% of polyps. While some of these missed polyps appear in the endoscopist’s field of view, others are missed simply because of substandard coverage of the procedure, i.e. not all of the colon is seen. This paper attempts to rectify the problem of substandard coverage in colonoscopy through the introduction of the C2D2 (Colonoscopy Coverage Deficiency via Depth) algorithm which detects deficient coverage, and can thereby alert the endoscopist to revisit a given area. More specifically, C2D2 consists of two separate algorithms: the first performs depth estimation of the colon given an ordinary RGB video stream; while the second computes coverage given these depth estimates. Rather than compute coverage for the entire colon, our algorithm computes coverage locally, on a segment-by-segment basis; C2D2 can then indicate in real-time whether a particular area of the colon has suffered from deficient coverage, and if so the endoscopist can return to that area. Our coverage algorithm is the first such algorithm to be evaluated in a large-scale way; while our depth estimation technique is the first calibration-free unsupervised method applied to colonoscopies. The C2D2 algorithm achieves state of the art results in the detection of deficient coverage. On synthetic sequences with ground truth, it is 2.4 times more accurate than human experts; while on real sequences, C2D2 achieves a 93.0% agreement with experts. |
| Tasks | Calibration, Depth Estimation |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08589v3 |
| https://arxiv.org/pdf/2001.08589v3.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-deficient-coverage-in-colonoscopies |
| Repo | |
| Framework | |
Autocamera Calibration for traffic surveillance cameras with wide angle lenses
| Title | Autocamera Calibration for traffic surveillance cameras with wide angle lenses |
| Authors | Aman Gajendra Jain, Nicolas Saunier |
| Abstract | We propose a method for automatic calibration of a traffic surveillance camera with wide-angle lenses. Video footage of a few minutes is sufficient for the entire calibration process to take place. This method takes in the height of the camera from the ground plane as the only user input to overcome the scale ambiguity. The calibration is performed in two stages, 1. Intrinsic Calibration 2. Extrinsic Calibration. Intrinsic calibration is achieved by assuming an equidistant fisheye distortion and an ideal camera model. Extrinsic calibration is accomplished by estimating the two vanishing points, on the ground plane, from the motion of vehicles at perpendicular intersections. The first stage of intrinsic calibration is also valid for thermal cameras. Experiments have been conducted to demonstrate the effectiveness of this approach on visible as well as thermal cameras. Index Terms: fish-eye, calibration, thermal camera, intelligent transportation systems, vanishing points |
| Tasks | Calibration |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.07243v1 |
| https://arxiv.org/pdf/2001.07243v1.pdf | |
| PWC | https://paperswithcode.com/paper/autocamera-calibration-for-traffic |
| Repo | |
| Framework | |
Machine learning for total cloud cover prediction
| Title | Machine learning for total cloud cover prediction |
| Authors | Ágnes Baran, Sebastian Lerch, Mehrez El Ayari, Sándor Baran |
| Abstract | Accurate and reliable forecasting of total cloud cover (TCC) is vital for many areas such as astronomy, energy demand and production, or agriculture. Most meteorological centres issue ensemble forecasts of TCC, however, these forecasts are often uncalibrated and exhibit worse forecast skill than ensemble forecasts of other weather variables. Hence, some form of post-processing is strongly required to improve predictive performance. As TCC observations are usually reported on a discrete scale taking just nine different values called oktas, statistical calibration of TCC ensemble forecasts can be considered a classification problem with outputs given by the probabilities of the oktas. This is a classical area where machine learning methods are applied. We investigate the performance of post-processing using multilayer perceptron (MLP) neural networks, gradient boosting machines (GBM) and random forest (RF) methods. Based on the European Centre for Medium-Range Weather Forecasts global TCC ensemble forecasts for 2002-2014 we compare these approaches with the proportional odds logistic regression (POLR) and multiclass logistic regression (MLR) models, as well as the raw TCC ensemble forecasts. We further assess whether improvements in forecast skill can be obtained by incorporating ensemble forecasts of precipitation as additional predictor. Compared to the raw ensemble, all calibration methods result in a significant improvement in forecast skill. RF models provide the smallest increase in predictive performance, while MLP, POLR and GBM approaches perform best. The use of precipitation forecast data leads to further improvements in forecast skill and except for very short lead times the extended MLP model shows the best overall performance. |
| Tasks | Calibration |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05948v1 |
| https://arxiv.org/pdf/2001.05948v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-total-cloud-cover |
| Repo | |
| Framework | |
Correcting Decalibration of Stereo Cameras in Self-Driving Vehicles
| Title | Correcting Decalibration of Stereo Cameras in Self-Driving Vehicles |
| Authors | Jon Muhovič, Janez Perš |
| Abstract | We address the problem of optical decalibration in mobile stereo camera setups, especially in context of autonomous vehicles. In real world conditions, an optical system is subject to various sources of anticipated and unanticipated mechanical stress (vibration, rough handling, collisions). Mechanical stress changes the geometry between the cameras that make up the stereo pair, and as a consequence, the pre-calculated epipolar geometry is no longer valid. Our method is based on optimization of camera geometry parameters and plugs directly into the output of the stereo matching algorithm. Therefore, it is able to recover calibration parameters on image pairs obtained from a decalibrated stereo system with minimal use of additional computing resources. The number of successfully recovered depth pixels is used as an objective function, which we aim to maximize. Our simulation confirms that the method can run constantly in parallel to stereo estimation and thus help keep the system calibrated in real time. Results confirm that the method is able to recalibrate all the parameters except for the baseline distance, which scales the absolute depth readings. However, that scaling factor could be uniquely determined using any kind of absolute range finding methods (e.g. a single beam time-of-flight sensor). |
| Tasks | Autonomous Vehicles, Calibration, Stereo Matching |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05267v1 |
| https://arxiv.org/pdf/2001.05267v1.pdf | |
| PWC | https://paperswithcode.com/paper/correcting-decalibration-of-stereo-cameras-in |
| Repo | |
| Framework | |
NeuralSens: Sensitivity Analysis of Neural Networks
| Title | NeuralSens: Sensitivity Analysis of Neural Networks |
| Authors | J. Pizarroso, J. Portela, A. Muñoz |
| Abstract | Neural networks are important tools for data-intensive analysis and are commonly applied to model non-linear relationships between dependent and independent variables. However, neural networks are usually seen as “black boxes” that offer minimal information about how the input variables are used to predict the response in a fitted model. This article describes the \pkg{NeuralSens} package that can be used to perform sensitivity analysis of neural networks using the partial derivatives method. Functions in the package can be used to obtain the sensitivities of the output with respect to the input variables, evaluate variable importance based on sensitivity measures and characterize relationships between input and output variables. Methods to calculate sensitivities are provided for objects from common neural network packages in \proglang{R}, including \pkg{neuralnet}, \pkg{nnet}, \pkg{RSNNS}, \pkg{h2o}, \pkg{neural}, \pkg{forecast} and \pkg{caret}. The article presents an overview of the techniques for obtaining information from neural network models, a theoretical foundation of how are calculated the partial derivatives of the output with respect to the inputs of a multi-layer perceptron model, a description of the package structure and functions, and applied examples to compare \pkg{NeuralSens} functions with analogous functions from other available \proglang{R} packages. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11423v1 |
| https://arxiv.org/pdf/2002.11423v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuralsens-sensitivity-analysis-of-neural |
| Repo | |
| Framework | |
Online Learning for Active Cache Synchronization
| Title | Online Learning for Active Cache Synchronization |
| Authors | Andrey Kolobov, Sébastien Bubeck, Julian Zimmert |
| Abstract | Existing multi-armed bandit (MAB) models make two implicit assumptions: an arm generates a payoff only when it is played, and the agent observes every payoff that is generated. This paper introduces synchronization bandits, a MAB variant where all arms generate costs at all times, but the agent observes an arm’s instantaneous cost only when the arm is played. Synchronization MABs are inspired by online caching scenarios such as Web crawling, where an arm corresponds to a cached item and playing the arm means downloading its fresh copy from a server. We present MirrorSync, an online learning algorithm for synchronization bandits, establish an adversarial regret of $O(T^{2/3})$ for it, and show how to make it efficient in practice. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12014v1 |
| https://arxiv.org/pdf/2002.12014v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-for-active-cache |
| Repo | |
| Framework | |
A Survey on The Expressive Power of Graph Neural Networks
| Title | A Survey on The Expressive Power of Graph Neural Networks |
| Authors | Ryoma Sato |
| Abstract | Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have been proposed to overcome these limitations. In this survey, we provide a comprehensive overview of the expressive power of GNNs and provably powerful variants of GNNs. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04078v2 |
| https://arxiv.org/pdf/2003.04078v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-the-expressive-power-of-graph |
| Repo | |
| Framework | |
Inducing Equilibria in Networked Public Goods Games through Network Structure Modification
| Title | Inducing Equilibria in Networked Public Goods Games through Network Structure Modification |
| Authors | David Kempe, Sixie Yu, Yevgeniy Vorobeychik |
| Abstract | Networked public goods games model scenarios in which self-interested agents decide whether or how much to invest in an action that benefits not only themselves, but also their network neighbors. Examples include vaccination, security investment, and crime reporting. While every agent’s utility is increasing in their neighbors’ joint investment, the specific form can vary widely depending on the scenario. A principal, such as a policymaker, may wish to induce large investment from the agents. Besides direct incentives, an important lever here is the network structure itself: by adding and removing edges, for example, through community meetings, the principal can change the nature of the utility functions, resulting in different, and perhaps socially preferable, equilibrium outcomes. We initiate an algorithmic study of targeted network modifications with the goal of inducing equilibria of a particular form. We study this question for a variety of equilibrium forms (induce all agents to invest, at least a given set $S$, exactly a given set $S$, at least $k$ agents), and for a variety of utility functions. While we show that the problem is NP-complete for a number of these scenarios, we exhibit a broad array of scenarios in which the problem can be solved in polynomial time by non-trivial reductions to (minimum-cost) matching problems. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.10627v1 |
| https://arxiv.org/pdf/2002.10627v1.pdf | |
| PWC | https://paperswithcode.com/paper/inducing-equilibria-in-networked-public-goods |
| Repo | |
| Framework | |
A random forest based approach for predicting spreads in the primary catastrophe bond market
| Title | A random forest based approach for predicting spreads in the primary catastrophe bond market |
| Authors | Despoina Makariou, Pauline Barrieu, Yining Chen |
| Abstract | We introduce a random forest approach to enable spreads’ prediction in the primary catastrophe bond market. We investigate whether all information provided to investors in the offering circular prior to a new issuance is equally important in predicting its spread. The whole population of non-life catastrophe bonds issued from December 2009 to May 2018 is used. The random forest shows an impressive predictive power on unseen primary catastrophe bond data explaining 93% of the total variability. For comparison, linear regression, our benchmark model, has inferior predictive performance explaining only 47% of the total variability. All details provided in the offering circular are predictive of spread but in a varying degree. The stability of the results is studied. The usage of random forest can speed up investment decisions in the catastrophe bond industry. |
| Tasks | |
| Published | 2020-01-28 |
| URL | https://arxiv.org/abs/2001.10393v1 |
| https://arxiv.org/pdf/2001.10393v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-random-forest-based-approach-for-predicting |
| Repo | |
| Framework | |
Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks
| Title | Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks |
| Authors | Jacob Schrum, Jake Gutierrez, Vanessa Volz, Jialin Liu, Simon Lucas, Sebastian Risi |
| Abstract | Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data, and a real-valued evolutionary algorithm can search that latent space. Such Latent Variable Evolution (LVE) has recently been applied to game levels. However, it is hard for objective scores to capture level features that are appealing to players. Therefore, this paper introduces a tool for interactive LVE of tile-based levels for games. The tool also allows for direct exploration of the latent dimensions, and allows users to play discovered levels. The tool works for a variety of GAN models trained for both Super Mario Bros. and The Legend of Zelda, and is easily generalizable to other games. A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels. User feedback also indicates how this system could eventually grow into a commercial design tool, with the addition of a few enhancements. |
| Tasks | |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2004.00151v1 |
| https://arxiv.org/pdf/2004.00151v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-evolution-and-exploration-within |
| Repo | |
| Framework | |
Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
| Title | Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching |
| Authors | Rémi Giraud, Yannick Berthoumieu |
| Abstract | Superpixels are widely used in computer vision applications. Nevertheless, decomposition methods may still fail to efficiently cluster image pixels according to their local texture. In this paper, we propose a new Nearest Neighbor-based Superpixel Clustering (NNSC) method to generate texture-aware superpixels in a limited computational time compared to previous approaches. We introduce a new clustering framework using patch-based nearest neighbor matching, while most existing methods are based on a pixel-wise K-means clustering. Therefore, we directly group pixels in the patch space enabling to capture texture information. We demonstrate the efficiency of our method with favorable comparison in terms of segmentation performances on both standard color and texture datasets. We also show the computational efficiency of NNSC compared to recent texture-aware superpixel methods. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04414v1 |
| https://arxiv.org/pdf/2003.04414v1.pdf | |
| PWC | https://paperswithcode.com/paper/texture-superpixel-clustering-from-patch |
| Repo | |
| Framework | |
Features for Ground Texture Based Localization – A Survey
| Title | Features for Ground Texture Based Localization – A Survey |
| Authors | Jan Fabian Schmid, Stephan F. Simon, Rudolf Mester |
| Abstract | Ground texture based vehicle localization using feature-based methods is a promising approach to achieve infrastructure-free high-accuracy localization. In this paper, we provide the first extensive evaluation of available feature extraction methods for this task, using separately taken image pairs as well as synthetic transformations. We identify AKAZE, SURF and CenSurE as best performing keypoint detectors, and find pairings of CenSurE with the ORB, BRIEF and LATCH feature descriptors to achieve greatest success rates for incremental localization, while SIFT stands out when considering severe synthetic transformations as they might occur during absolute localization. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.11948v2 |
| https://arxiv.org/pdf/2002.11948v2.pdf | |
| PWC | https://paperswithcode.com/paper/features-for-ground-texture-based |
| Repo | |
| Framework | |
