no code implementations • 2 Mar 2024 • Ziting Wen, Oscar Pizarro, Stefan Williams
Fine-tuning the pre-trained model with active learning holds promise for reducing annotation costs.
no code implementations • 7 Jun 2023 • Ziting Wen, Oscar Pizarro, Stefan Williams
Recent research has shown that in the context of supervised learning different active learning strategies need to be applied at various stages of the training process to ensure improved performance over the random baseline.
no code implementations • 7 Jun 2023 • Suraj Bijjahalli, Oscar Pizarro, Stefan B. Williams
We evaluate the precision-recall tradeoff and demonstrate that by choosing an appropriate latent dimensionality and threshold, we are able to achieve an average precision of 0. 64 on unlabelled datasets.
1 code implementation • 20 Mar 2023 • Heather Doig, Oscar Pizarro, Stefan B. Williams
We adapt the SymmNet state-of-the-art Unsupervised Domain Adaptation method with an efficient bilinear pooling layer and image scaling to normalise spatial resolution, and show improved classification accuracy.
no code implementations • 9 Mar 2022 • Ziting Wen, Oscar Pizarro, Stefan Williams
Consequently, our framework can significantly improve the performance of models in the case of few annotations while reducing the training time.
no code implementations • 13 Aug 2021 • Takaki Yamada, Adam Prügel-Bennett, Stefan B. Williams, Oscar Pizarro, Blair Thornton
We demonstrate how the latent representations generated by GeoCLR can be used to efficiently guide human annotation efforts, where the semi-supervised framework improves classification accuracy by an average of 10. 2% compared to the state-of-the-art SimCLR using the same CNN and equivalent number of human annotations for training.
no code implementations • 25 May 2021 • Jackson Shields, Oscar Pizarro, Stefan B. Williams
This research proposes methods for planning initial AUV surveys that efficiently explore a feature space representation of the bathymetry, in order to sample from a diverse set of bathymetric terrain.
no code implementations • 20 Jun 2020 • Jackson Shields, Oscar Pizarro, Stefan B. Williams
One such application is in benthic habitat mapping where these vehicles collect seafloor imagery that complements broadscale bathymetric data collected using sonar.
no code implementations • CVPR 2013 • Donald G. Dansereau, Oscar Pizarro, Stefan B. Williams
Results include calibration of a commercially available camera using three calibration grid sizes over five datasets.