SCASeg proposes a strip cross-attention decoder with lateral connections and a cross-layer block to efficiently capture global-local context, reporting competitive or superior results on ADE20K, Cityscapes, COCO-Stuff, and Pascal VOC.
Cmt: Convolutional neural networks meet vision transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation
SCASeg proposes a strip cross-attention decoder with lateral connections and a cross-layer block to efficiently capture global-local context, reporting competitive or superior results on ADE20K, Cityscapes, COCO-Stuff, and Pascal VOC.