Searched for: author%3A%22Lengyel%2C+A.%22
(1 - 6 of 6)
document
Lengyel, A. (author)
Computer vision algorithms are getting more advanced by the day and slowly approach human-like capabilities, such as detecting objects in cluttered scenes and recognizing facial expressions. Yet, computers learn to perform these tasks very differently from humans. Where humans can generalize between different lighting conditions or geometric...
doctoral thesis 2024
document
Warchocki, J. (author), Oprescu, T. (author), Wang, Y. (author), Dămăcuș, A. (author), Misterka, P.M. (author), Bruintjes, R. (author), Lengyel, A. (author), Strafforello, O. (author), van Gemert, J.C. (author)
In temporal action localization, given an input video, the goal is to predict which actions it contains, where they begin, and where they end. Training and testing current state-of- the-art deep learning models requires access to large amounts of data and computational power. However, gathering such data is challenging and computational...
conference paper 2023
document
Edixhoven, T.F. (author), Lengyel, A. (author), van Gemert, J.C. (author)
In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to the rotation and reflection symmetries. We focus on the 2D rotations and reflections and investigate the impact of the broken equivariance on network performance. We show that a change in the input dimension of a network...
conference paper 2023
document
Lengyel, A. (author), Strafforello, O. (author), Bruintjes, R. (author), Gielisse, A.S. (author), van Gemert, J.C. (author)
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 removing all color information, which sacrifices...
conference paper 2023
document
Zeng, L. (author), Lengyel, A. (author), Tömen, N. (author), van Gemert, J.C. (author)
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 self-supervised depth estimation. We argue that the semantics of a coherent group of pixels in 3D space is self-contained and invariant to the contexts in which they...
conference paper 2022
document
Lengyel, A. (author), Garg, Sourav (author), Milford, Michael (author), van Gemert, J.C. (author)
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 unlabeled data samples from the test set. As gathering relevant test data is expensive and sometimes even impossible, we remove any reliance on test data imagery and...
conference paper 2021
Searched for: author%3A%22Lengyel%2C+A.%22
(1 - 6 of 6)