A diffusion U-Net's attention features, aligned with a bidirectional attention score, can rank visual similarity competitively with CLIP, DINO, and LPIPS.
Flux.1 ai, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
A diffusion U-Net's attention features, aligned with a bidirectional attention score, can rank visual similarity competitively with CLIP, DINO, and LPIPS.