Search Results for author: Michal Mackiewicz

Found 10 papers, 3 papers with code

Extending Temporal Data Augmentation for Video Action Recognition

no code implementations9 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.

Action Recognition Data Augmentation

Colour augmentation for improved semi-supervised semantic segmentation

no code implementations9 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.

Classification Self-Supervised Learning +1

Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptation

no code implementations19 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.

Unsupervised Domain Adaptation

Semi-supervised semantic segmentation needs strong, high-dimensional perturbations

no code implementations25 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.

Semi-Supervised Semantic Segmentation

Using Deep Learning to Count Albatrosses from Space

no code implementations3 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.

Image Segmentation Semantic Segmentation

Semi-supervised semantic segmentation needs strong, varied perturbations

3 code implementations5 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.

General Classification Semi-Supervised Semantic Segmentation

Spherical sampling methods for the calculation of metamer mismatch volumes

no code implementations23 Jan 2019 Michal Mackiewicz, Hans Jakob Rivertz, Graham D. Finlayson

In this paper, we propose two methods of calculating theoretically maximal metamer mismatch volumes.

Cannot find the paper you are looking for? You can Submit a new open access paper.