← Search

Robert-Jan Bruintjes

2 accepted papers

2023

Color Equivariant Convolutional Networks

NeurIPS 2023poster

Color is a crucial visual cue readily exploited by Convolutional Neural Networks (CNNs) for object recognition. However, CNNs struggle if there is data imbalance between color variations introduced by accidental recording conditions. Color invariance addresses this issue but does so at the cost of r…

2022

FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes

ICLR 2022poster

When designing Convolutional Neural Networks (CNNs), one must select the size of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but exploring all possible combinations is unfeasible in practice. A more efficient approach is…