Location-aware training improves seafloor image classification for CNN-style self-supervised models, but a pretrained vision transformer matches the best location-regularised result without any fine-tuning.
ugel-Bennett, S. B. Williams, O. Pizarro, and B. Thornton, “Geoclr: Georeference contrastive learning for efficient seafloor image interpretation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Investigating Location-Regularised Self-Supervised Feature Learning for Seafloor Visual Imagery
Location-aware training improves seafloor image classification for CNN-style self-supervised models, but a pretrained vision transformer matches the best location-regularised result without any fine-tuning.