Tackling Structural Hallucination in Image Translation with Local Diffusion
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RIBCHTILrecord.jsonopen to challenge →
read the original abstract
Recent developments in diffusion models have advanced conditioned image generation, yet they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in medical images, causing "image hallucination" and risking misdiagnosis. We hypothesize such hallucinations result from local OOD regions in the conditional images. We verify that partitioning the OOD region and conducting separate image generations alleviates hallucinations in several applications. From this, we propose a training-free diffusion framework that reduces hallucination with multiple Local Diffusion processes. Our approach involves OOD estimation followed by two modules: a "branching" module generates locally both within and outside OOD regions, and a "fusion" module integrates these predictions into one. Our evaluation shows our method mitigates hallucination over baseline models quantitatively and qualitatively, reducing misdiagnosis by 40% and 25% in the real-world medical and natural image datasets, respectively. It also demonstrates compatibility with various pre-trained diffusion models.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Score-Control for Hallucination Reduction in Diffusion Models
VSM modulates the score Jacobian using variance guidance to reduce hallucinations in diffusion models by up to 25% on synthetic and real datasets while preserving fidelity and diversity.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.