3 code implementations • ICLR 2018 • Geoffrey French, Michal Mackiewicz, Mark Fisher
This paper explores the use of self-ensembling for visual domain adaptation problems.
Ranked #1 on Domain Adaptation on Synth Signs-to-GTSRB
no code implementations • 23 Jan 2019 • Michal Mackiewicz, Hans Jakob Rivertz, Graham D. Finlayson
In this paper, we propose two methods of calculating theoretically maximal metamer mismatch volumes.
5 code implementations • 5 Jun 2019 • Geoff French, Samuli Laine, Timo Aila, Michal Mackiewicz, Graham Finlayson
We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success.
no code implementations • 3 Jul 2019 • Ellen Bowler, Peter T. Fretwell, Geoffrey French, Michal Mackiewicz
In this paper we test the use of a deep learning approach to automatically count Wandering Albatrosses in Very High Resolution (VHR) satellite imagery.
no code implementations • 25 Sep 2019 • Geoff French, Timo Aila, Samuli Laine, Michal Mackiewicz, Graham Finlayson
Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems.
no code implementations • 19 Aug 2020 • Artjoms Gorpincenko, Geoffrey French, Michal Mackiewicz
Virtual Adversarial Training has recently seen a lot of success in semi-supervised learning, as well as unsupervised Domain Adaptation.
no code implementations • 6 Mar 2021 • Artjoms Gorpincenko, Geoffrey French, Peter Knight, Mike Challiss, Michal Mackiewicz
Human enterprise often suffers from direct negative effects caused by jellyfish blooms.
no code implementations • 9 Oct 2021 • Geoff French, Michal Mackiewicz
Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification.
1 code implementation • 18 Nov 2021 • Hang Zhou, Sarah Taylor, David Greenwood, Michal Mackiewicz
Depth models trained with SUB-Depth outperform the same models trained in a standard single-task SDE framework.
no code implementations • 9 Nov 2022 • Artjoms Gorpincenko, Michal Mackiewicz
Pixel space augmentation has grown in popularity in many Deep Learning areas, due to its effectiveness, simplicity, and low computational cost.
no code implementations • 12 Sep 2023 • Mazvydas Gudelis, Michal Mackiewicz, Julie Bremner, Sophie Fielding
British Antarctic Survey (BAS) researchers launch annual expeditions to the Antarctic in order to estimate Antarctic Krill biomass and assess the change from previous years.