Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Bujwid, Sebastian"'
Autor:
Rabadán, Miquel Martí i, Bujwid, Sebastian, Pieropan, Alessandro, Azizpour, Hossein, Maki, Atsuto
Publikováno v:
Vol. 3 (2022): Proceedings of the Northern Lights Deep Learning Workshop 2022
Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. We compare it to an alternative setting where each mini-batch is unifor
Externí odkaz:
http://arxiv.org/abs/2201.00604
Autor:
Bujwid, Sebastian, Sullivan, Josephine
We study the impact of using rich and diverse textual descriptions of classes for zero-shot learning (ZSL) on ImageNet. We create a new dataset ImageNet-Wiki that matches each ImageNet class to its corresponding Wikipedia article. We show that merely
Externí odkaz:
http://arxiv.org/abs/2103.09669
Autor:
Bujwid, Sebastian
In this work, we propose a novel and effective method for constraining the output space of the ill-posed problem of unsupervised image-to-image translation. We make the assumption that the environment of the source domain is known, and we propose to
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233849
Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageable diversity of real-words situations. The main issue with unpaired ima
Externí odkaz:
http://arxiv.org/abs/1812.01710
Autor:
Bujwid, Sebastian
In this work, we propose a novel and effective method for constraining the output space of the ill-posed problem of unsupervised image-to-image translation. We make the assumption that the environment of the source domain is known, and we propose to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f4612541d7f3eacdfde934084de6b851
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233849
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233849