activity
20202022
most citedVIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

11 citations · 14 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CV2022

Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation

Liang Zeng, Attila Lengyel, Nergis Tömen +1

In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily available for training…

cs.CV2022

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios +4

The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scra…

cs.CV2021

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…

cs.CV2021

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…

cs.CV2021

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…

cs.CV202111 cited

VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios +2

We present the first edition of "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges. We offer four data-impaired challenges, where models are trained fr…