no code implementations • 11 Mar 2022 • Thomas Verelst, Paul K. Rubenstein, Marcin Eichner, Tinne Tuytelaars, Maxim Berman
We show that adding a consistency loss, ensuring that the predictions of the network are consistent over consecutive training epochs, is a simple yet effective method to train multi-label classifiers in a weakly supervised setting.
1 code implementation • ICCV 2021 • Thomas Verelst, Tinne Tuytelaars
In this paper we propose BlockCopy, a scheme that accelerates pretrained frame-based CNNs to process video more efficiently, compared to standard frame-by-frame processing.
1 code implementation • 24 Nov 2020 • Thomas Verelst, Tinne Tuytelaars
For instance, our method reduces the number of floating-point operations of SwiftNet-RN18 by 60% and increases the inference speed by 50%, with only 0. 3% decrease in mIoU accuracy on Cityscapes.
Ranked #6 on Semantic Segmentation on Mapillary val
1 code implementation • CVPR 2020 • Thomas Verelst, Tinne Tuytelaars
Modern convolutional neural networks apply the same operations on every pixel in an image.
no code implementations • 11 Mar 2019 • Thomas Verelst, Matthew Blaschko, Maxim Berman
Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization.