77 citations · 124 across the 17 of their papers we have counts for
7 papers · 2 filters
Domain Adaptation for Rare Classes Augmented with Synthetic Samples
Tuhin Das, Robert-Jan Bruintjes, Attila Lengyel +2
To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain…
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak +3
When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kern…
Zero-Shot Day-Night Domain Adaptation with a Physics Prior
Attila Lengyel, Sourav Garg, Michael Milford +1
We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting u…
Exploiting Learned Symmetries in Group Equivariant Convolutions
Attila Lengyel, Jan C. van Gemert
Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost. We…
Resolution learning in deep convolutional networks using scale-space theory
Silvia L. Pintea, Nergis Tomen, Stanley F. Goes +2
Resolution in deep convolutional neural networks (CNNs) is typically bounded by the receptive field size through filter sizes, and subsampling layers or strided convolutions on fea…
No frame left behind: Full Video Action Recognition
Xin Liu, Silvia L. Pintea, Fatemeh Karimi Nejadasl +2
Not all video frames are equally informative for recognizing an action. It is computationally infeasible to train deep networks on all video frames when actions develop over hundre…