no code implementations • 25 Mar 2024 • Pengcheng Hao, Oktay Karakus, Alin Achim
Driven by the filtering challenges in linear systems disturbed by non-Gaussian heavy-tailed noise, the robust Kalman filters (RKFs) leveraging diverse heavy-tailed distributions have been introduced.
no code implementations • 7 Feb 2024 • Wanli Ma, Oktay Karakus, Paul L. Rosin
The proposed semi-supervised learning-based knowledge distillation (SSLKD) approach demonstrates a notable improvement in the performance of the student model, in the application of road segmentation, surpassing the effectiveness of traditional semi-supervised learning methods.
no code implementations • 22 Nov 2023 • Wanli Ma, Oktay Karakus, Paul L. Rosin
There is still a lack of lightweight and efficient perturbation methods to promote the diversity of features and the precision of pseudo labels during training.
no code implementations • 17 May 2023 • Wanli Ma, Oktay Karakus, Paul L. Rosin
Especially in the application of land cover classification, pixel-level manual labelling in large-scale imagery is labour-intensive, time-consuming and expensive.
no code implementations • 11 Oct 2022 • Henry Booth, Wanli Ma, Oktay Karakus
As such, this paper comprised of three main components: (1) the development of a machine learning model, (2) the construction of the MAP-Mapper, an automated tool for mapping marine-plastic density, and finally (3) an evaluation of the whole system for out-of-distribution test locations.
3 code implementations • 10 Mar 2020 • Oktay Karakus, Perla Mayo, Alin Achim
In this paper, we propose a proximal splitting methodology with a non-convex penalty function based on the heavy-tailed Cauchy distribution.