Self-supervised MAE pre-training on unlabeled SAR images raises SARDet-100k object detection from 53.6 to 54.9 mAP, 1.3 points above ImageNet pre-training.
Masked autoencoders are scalable vision learners,
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
background 1representative citing papers
citing papers explorer
-
Enhancing SAR Object Detection with Self-Supervised Pre-training on Masked Auto-Encoders
Self-supervised MAE pre-training on unlabeled SAR images raises SARDet-100k object detection from 53.6 to 54.9 mAP, 1.3 points above ImageNet pre-training.