1 code implementation • 18 Jan 2024 • Wouter Van Gansbeke, Bert de Brabandere
Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to handle the permutation-invariance of the instance masks.
no code implementations • 12 Oct 2021 • Robby Neven, Davy Neven, Bert de Brabandere, Marc Proesmans, Toon Goedemé
In this paper, we present a new loss function to train a segmentation network with only a small subset of pixel-perfect labels, but take the advantage of weakly-annotated training samples in the form of cheap bounding-box labels.
4 code implementations • CVPR 2019 • Davy Neven, Bert de Brabandere, Marc Proesmans, Luc van Gool
In this work we propose a new clustering loss function for proposal-free instance segmentation.
Ranked #1000000000 on Instance Segmentation on Cityscapes test
no code implementations • ICLR 2020 • Simon Vandenhende, Stamatios Georgoulis, Bert de Brabandere, Luc van Gool
In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand.
no code implementations • 8 Mar 2019 • Simon Vandenhende, Bert de Brabandere, Davy Neven, Luc van Gool
The generator's objective is to synthesize samples that are both realistic and hard to label for the classifier.
1 code implementation • 14 Feb 2019 • Wouter Van Gansbeke, Davy Neven, Bert de Brabandere, Luc van Gool
However, we additionally propose a fusion method with RGB guidance from a monocular camera in order to leverage object information and to correct mistakes in the sparse input.
Ranked #5 on Depth Completion on KITTI Depth Completion
1 code implementation • arXiv 2019 • Wouter Van Gansbeke, Davy Neven, Bert de Brabandere, Luc van Gool
For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions.
1 code implementation • 1 Feb 2019 • Wouter Van Gansbeke, Bert de Brabandere, Davy Neven, Marc Proesmans, Luc van Gool
The problem with such a two-step approach is that the parameters of the network are not optimized for the true task of interest (estimating the lane curvature parameters) but for a proxy task (segmenting the lane markings), resulting in sub-optimal performance.
22 code implementations • 15 Feb 2018 • Davy Neven, Bert de Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc van Gool
By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation.
Ranked #15 on Lane Detection on TuSimple
1 code implementation • 8 Aug 2017 • Davy Neven, Bert de Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc van Gool
Most approaches for instance-aware semantic labeling traditionally focus on accuracy.
8 code implementations • 8 Aug 2017 • Bert De Brabandere, Davy Neven, Luc van Gool
In this work we propose to tackle the problem with a discriminative loss function, operating at the pixel level, that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step.
Ranked #4 on Multi-Human Parsing on MHP v1.0
no code implementations • 2 Jun 2017 • Jörn-Henrik Jacobsen, Bert de Brabandere, Arnold W. M. Smeulders
Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account.
1 code implementation • NeurIPS 2016 • Bert De Brabandere, Xu Jia, Tinne Tuytelaars, Luc van Gool
In a traditional convolutional layer, the learned filters stay fixed after training.
Ranked #1 on Video Prediction on KTH (Cond metric)
no code implementations • 22 Mar 2016 • Bert Moons, Bert de Brabandere, Luc van Gool, Marian Verhelst
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.