Výsledky vyhledávání - "Bert De Brabandere"

Weakly-Supervised Semantic Segmentation by Learning Label Uncertainty

Autor: Robby Neven, Toon Goedemé, Davy Neven, Marc Proesmans, Bert De Brabandere

Sinds de opkomst van deep learning kent het domein van computervisie een enorme vooruitgang op het gebied van semantische segmentatie. Echter, om een hoge performantie te bekomen is een nauwkeurig gelabelde dataset nodig, welke een grote kost met zic

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::229c0c48af4b79b30c5f8ca4c5941808

Zobrazit plný text záznamu

Object-Centric Street Scene Synthesis with Generative Adversarial Networks

Autor: Marc Proesmans, Davy Neven, Bert De Brabandere, Luc Van Gool, Maxim Van den Abeele

Publikováno v: 2020 IEEE 20th Mediterranean Electrotechnical Conference ( MELECON).

We present a new method to synthesise street scene images from instance information using a conditional Generative Adversarial Network (GAN). These conditional GANs made a variety of applications possible, but remain limited to lower resolutions. The

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::933f53bb10e4b2a0d6726036b1c4d9a2
https://doi.org/10.1109/melecon48756.2020.9140547

Zobrazit plný text záznamu

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

Autor: Marc Proesmans, Luc Van Gool, Davy Neven, Bert De Brabandere

Publikováno v: CVPR

Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high accuracy,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42a849b4db54fb57dcfddae022348ade
https://doi.org/10.1109/cvpr.2019.00904

Zobrazit plný text záznamu

Sparse and Noisy LiDAR Completion with RGB Guidance and Uncertainty

Autor: Wouter Van Gansbeke, Bert De Brabandere, Luc Van Gool, Davy Neven

Publikováno v: MVA

This work proposes a new method to accurately complete sparse LiDAR maps guided by RGB images. For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions. A multitude of applications depend on

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa9eea9a0e39407f3b57e33e44c98679
https://doi.org/10.23919/mva.2019.8757939

Zobrazit plný text záznamu

End-to-end Lane Detection through Differentiable Least-Squares Fitting

Autor: Marc Proesmans, Davy Neven, Luc Van Gool, Bert De Brabandere, Wouter Van Gansbeke

Publikováno v: ICCV Workshops

Lane detection is typically tackled with a two-step pipeline in which a segmentation mask of the lane markings is predicted first, and a lane line model (like a parabola or spline) is fitted to the post-processed mask next. The problem with such a tw

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9aa0af590b9bd37227191e47d777905
http://arxiv.org/abs/1902.00293

Zobrazit plný text záznamu

A Three-Player GAN: Generating Hard Samples To Improve Classification Networks

Autor: Davy Neven, Bert De Brabandere, Simon Vandenhende, Luc Van Gool

Publikováno v: MVA

We propose a Three-Player Generative Adversarial Network to improve classification networks. In addition to the game played between the discriminator and generator, a competition is introduced between the generator and the classifier. The generator's

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d5a3ad7ccf638f598de81c60c7ff0d6

Zobrazit plný text záznamu

From Pixels to Actions: Learning to Drive a Car with Deep Neural Networks

Autor: Seppe Iven, M José Oramas, Jonas Heylen, Bert De Brabandere, Luc Van Gool, Tinne Tuytelaars

Publikováno v: WACV

© 2018 IEEE. The promise of self-driving cars promotes several advantages, e.g. they have the ability to outperform human drivers while being safer. Here we take a deeper look into some aspects from algorithms aimed at making this promise a reality.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e2245d0941997a8c870829eb087e945
https://doi.org/10.1109/wacv.2018.00072

Zobrazit plný text záznamu

Towards End-to-End Lane Detection: an Instance Segmentation Approach

Autor: Bert De Brabandere, Davy Neven, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool

Publikováno v: Intelligent Vehicles Symposium

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane departure or

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4756dc05c7bb488dd60e413174e60b04

Zobrazit plný text záznamu

Semantic instance segmentation for autonomous driving

Autor: Luc Van Gool, Davy Neven, Bert De Brabandere

Publikováno v: CVPR Workshops

© 2017 IEEE. Semantic instance segmentation remains a challenge. We propose to tackle the problem with a discriminative loss function, operating at pixel level, that encourages a convolutional network to produce a representation of the image that ca

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d10a202af3573441d22e6b315227fe54
https://lirias.kuleuven.be/handle/123456789/600003

Zobrazit plný text záznamu

Energy-Efficient ConvNets Through Approximate Computing

Autor: Marian Verhelst, Bert Moons, Bert De Brabandere, Luc Van Gool

Recently ConvNets or convolutional neural networks (CNN) have come up as state-of-the-art classification and detection algorithms, achieving near-human performance in visual detection. However, ConvNet algorithms are typically very computation and me

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c69169093c088aa2843dfd0897422ff
http://arxiv.org/abs/1603.06777

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání