PatchDPO scores each image patch by similarity to a reference and retrains personalized generators with patch-weighted losses, reporting higher DINO and CLIP-I on DreamBench than prior finetuning-free methods.
Training diffusion models with reinforce- ment learning
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
PatchDPO scores each image patch by similarity to a reference and retrains personalized generators with patch-weighted losses, reporting higher DINO and CLIP-I on DreamBench than prior finetuning-free methods.