A 42.9M-parameter UNet with a weighted IoU-Dice-cross-entropy loss is compared against a 200M-parameter MaskFormer on iSAID aerial segmentation, reporting mIoU 73.4 and 82.48 respectively.
ResUNet- a: A deep learning framework for semantic segmentation of remotely sensed data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery
A 42.9M-parameter UNet with a weighted IoU-Dice-cross-entropy loss is compared against a 200M-parameter MaskFormer on iSAID aerial segmentation, reporting mIoU 73.4 and 82.48 respectively.