EGFormer dynamically scores and drops the least useful sensor modality at each processing stage, cutting parameters by up to 91 percent and GFLOPs by half while keeping segmentation accuracy competitive.
Shapeconv: Shape-aware convolutional layer for indoor rgb-d semantic segmentation,
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
support 1representative citing papers
citing papers explorer
-
EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation
EGFormer dynamically scores and drops the least useful sensor modality at each processing stage, cutting parameters by up to 91 percent and GFLOPs by half while keeping segmentation accuracy competitive.