Pith. sign in

REVIEW 1 cited by

Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.14007 v1 pith:2N3SYIEM submitted 2024-04-22 cs.CV cs.AI

classification cs.CVcs.AI
keywords overfittingconceptcustomizedinfusionnon-customizedchallengeconceptscustomization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first analyze overfitting, categorizing it into concept-agnostic overfitting, which undermines non-customized concept knowledge, and concept-specific overfitting, which is confined to customize on limited modalities, i.e, backgrounds, layouts, styles. To evaluate the overfitting degree, we further introduce two metrics, i.e, Latent Fisher divergence and Wasserstein metric to measure the distribution changes of non-customized and customized concept respectively. Drawing from the analysis, we propose Infusion, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training modalities, while preserving non-customized knowledge. Remarkably, Infusion achieves this feat with remarkable efficiency, requiring a mere 11KB of trained parameters. Extensive experiments also demonstrate that our approach outperforms state-of-the-art methods in both single and multi-concept customized generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization

    cs.CV 2024-12 conditional novelty 6.0 of 10

    DECOR suppresses undesired word-token semantics in text embeddings via orthogonal projection, reducing prompt misalignment and content leakage in LoRA-customized text-to-image models.

Pith tools