A novel pre-training strategy for ImageNet-initialized models achieves state-of-the-art semantic segmentation performance on four remote sensing datasets (iSAID, MFNet, PST900, Potsdam) by reducing domain-specific feature learning during pre-training.
IEEE Transactions on Geoscience and Re- mote Sensing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
A novel pre-training strategy for ImageNet-initialized models achieves state-of-the-art semantic segmentation performance on four remote sensing datasets (iSAID, MFNet, PST900, Potsdam) by reducing domain-specific feature learning during pre-training.