FoR-Net improves efficiency in semantic segmentation by focusing on hard regions with a learned selector and multi-scale convolutions, achieving competitive results on Cityscapes.
Shufflenet: An extremely efficient convolutional neural network for mobile devices, in: CVPR
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
-
FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation
FoR-Net improves efficiency in semantic segmentation by focusing on hard regions with a learned selector and multi-scale convolutions, achieving competitive results on Cityscapes.