arXiv subjects

Dezső Ribli

Publications and source records attributed to Dezső Ribli.

5 recordsLinked to original sources

arXiv2023

aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception

Autonomous driving is a popular research area within the computer vision research community. Since autonomous vehicles are highly safety-critical, ensuring robustness is essential for real-world deployment. While several public multimodal datasets are accessible, they mainly comprise two sensor modalities (camera, LiDAR) which are not well suited for adverse weather. In addition, they lack far-range annotations, making it harder to train neural networks that are the base of a highway assistant function of an autonomous vehicle. Therefore, we introduce a multimodal dataset for robust autonomous driving with long-range perception. The dataset consists of 176 scenes with synchronized and calibrated LiDAR, camera, and radar sensors covering a 360-degree field of view. The collected data was captured in highway, urban, and suburban areas during daytime, night, and rain and is annotated with 3D bounding boxes with consistent identifiers across frames. Furthermore, we trained unimodal and multimodal baseline models for 3D object detection. Data are available at \url{https://github.com/aimotive/aimotive_dataset}.

cs.CV↗

arXiv2019

Galaxy shape measurement with convolutional neural networks

We present our results from training and evaluating a convolutional neural network (CNN) to predict galaxy shapes from wide-field survey images of the first data release of the Dark Energy Survey (DES DR1). We use conventional shape measurements as ground truth from an overlapping, deeper survey with less sky coverage, the Canada-France Hawaii Telescope Lensing Survey (CFHTLenS). We demonstrate that CNN predictions from single band DES images reproduce the results of CFHTLenS at bright magnitudes and show higher correlation with CFHTLenS at fainter magnitudes than maximum likelihood model fitting estimates in the DES Y1 im3shape catalogue. Prediction of shape parameters with a CNN is also extremely fast, it takes only 0.2 milliseconds per galaxy, improving more than 4 orders of magnitudes over forward model fitting. The CNN can also accurately predict shapes when using multiple images of the same galaxy, even in different color bands, with no additional computational overhead. The CNN is again more precise for faint objects, and the advantage of the CNN is more pronounced for blue galaxies than red ones when compared to the DES Y1 metacalibration catalogue, which fits a single Gaussian profile using riz band images. We demonstrate that CNN shape predictions within the metacalibration self-calibrating framework yield shear estimates with negligible multiplicative bias, $ m < 10^{-3}$, and no significant PSF leakage. Our proposed setup is applicable to current and next generation weak lensing surveys where higher quality ground truth shapes can be measured in dedicated deep fields.

astro-ph.CO↗

arXiv2019

Weak lensing cosmology with convolutional neural networks on noisy data

Weak gravitational lensing is one of the most promising cosmological probes of the late universe. Several large ongoing (DES, KiDS, HSC) and planned (LSST, EUCLID, WFIRST) astronomical surveys attempt to collect even deeper and larger scale data on weak lensing. Due to gravitational collapse, the distribution of dark matter is non-Gaussian on small scales. However, observations are typically evaluated through the two-point correlation function of galaxy shear, which does not capture non-Gaussian features of the lensing maps. Previous studies attempted to extract non-Gaussian information from weak lensing observations through several higher-order statistics such as the three-point correlation function, peak counts or Minkowski-functionals. Deep convolutional neural networks (CNN) emerged in the field of computer vision with tremendous success, and they offer a new and very promising framework to extract information from 2 or 3-dimensional astronomical data sets, confirmed by recent studies on weak lensing. We show that a CNN is able to yield significantly stricter constraints of ($σ_8, Ω_m$) cosmological parameters than the power spectrum using convergence maps generated by full N-body simulations and ray-tracing, at angular scales and shape noise levels relevant for future observations. In a scenario mimicking LSST or Euclid, the CNN yields 2.4-2.8 times smaller credible contours than the power spectrum, and 3.5-4.2 times smaller at noise levels corresponding to a deep space survey such as WFIRST. We also show that at shape noise levels achievable in future space surveys the CNN yields 1.4-2.1 times smaller contours than peak counts, a higher-order statistic capable of extracting non-Gaussian information from weak lensing maps.

astro-ph.CO↗

arXiv2018

An improved cosmological parameter inference scheme motivated by deep learning

Dark matter cannot be observed directly, but its weak gravitational lensing slightly distorts the apparent shapes of background galaxies, making weak lensing one of the most promising probes of cosmology. Several observational studies have measured the effect, and there are currently running, and planned efforts to provide even larger, and higher resolution weak lensing maps. Due to nonlinearities on small scales, the traditional analysis with two-point statistics does not fully capture all the underlying information. Multiple inference methods were proposed to extract more details based on higher order statistics, peak statistics, Minkowski functionals and recently convolutional neural networks (CNN). Here we present an improved convolutional neural network that gives significantly better estimates of $Ω_m$ and $σ_8$ cosmological parameters from simulated convergence maps than the state of art methods and also is free of systematic bias. We show that the network exploits information in the gradients around peaks, and with this insight, we construct a new, easy-to-understand, and robust peak counting algorithm based on the 'steepness' of peaks, instead of their heights. The proposed scheme is even more accurate than the neural network on high-resolution noiseless maps. With shape noise and lower resolution its relative advantage deteriorates, but it remains more accurate than peak counting.

astro-ph.CO↗

arXiv2017

Detecting and classifying lesions in mammograms with Deep Learning

In the last two decades Computer Aided Diagnostics (CAD) systems were developed to help radiologists analyze screening mammograms. The benefits of current CAD technologies appear to be contradictory and they should be improved to be ultimately considered useful. Since 2012 deep convolutional neural networks (CNN) have been a tremendous success in image recognition, reaching human performance. These methods have greatly surpassed the traditional approaches, which are similar to currently used CAD solutions. Deep CNN-s have the potential to revolutionize medical image analysis. We propose a CAD system based on one of the most successful object detection frameworks, Faster R-CNN. The system detects and classifies malignant or benign lesions on a mammogram without any human intervention. The proposed method sets the state of the art classification performance on the public INbreast database, AUC = 0.95 . The approach described here has achieved the 2nd place in the Digital Mammography DREAM Challenge with AUC = 0.85 . When used as a detector, the system reaches high sensitivity with very few false positive marks per image on the INbreast dataset. Source code, the trained model and an OsiriX plugin are availaible online at https://github.com/riblidezso/frcnn_cad .

cs.CV↗