A3-FPN augments multi-scale representations with asymptotic global interaction and content-aware resampling, delivering gains such as 49.6 mask AP on MS COCO when paired with OneFormer and Swin-L.
#$%& !"'$() coordinate offset (∆#, ∆$)attention weight ∆% coordinate offset (∆#, ∆$)attention weight ∆% resampled feature map resampled feature map !! !
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
-
A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
A3-FPN augments multi-scale representations with asymptotic global interaction and content-aware resampling, delivering gains such as 49.6 mask AP on MS COCO when paired with OneFormer and Swin-L.