GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation

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.

Contrastive Learning Transfer Learning