A hybrid CNN-transformer bottleneck segmentation model improves slightly on TopFormer and SeaFormer at equal FLOPs, but its state-of-the-art claim is contradicted by its own Table 2.
Deeplabv3+: Encoderde- coder with atrous separable convolution for semantic image segmentation [m]
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
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ContextFormer: Redefining Efficiency in Semantic Segmentation
A hybrid CNN-transformer bottleneck segmentation model improves slightly on TopFormer and SeaFormer at equal FLOPs, but its state-of-the-art claim is contradicted by its own Table 2.