A softmax and spatial attention fusion of SDXL base and refiner latents yields an ImageNet FID drop of about 1 point, but the result is not statistically supported.
CBAM: Convolutional Block Attention Module,
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.GR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Syn-thesis
A softmax and spatial attention fusion of SDXL base and refiner latents yields an ImageNet FID drop of about 1 point, but the result is not statistically supported.