Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Seo, Hoigi, Bang, Junseo, Lee, Haechang, Lee, Joohoon, Lee, Byung Hyun, Chun, Se Young
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908398455357440
author Seo, Hoigi
Bang, Junseo
Lee, Haechang
Lee, Joohoon
Lee, Byung Hyun
Chun, Se Young
author_facet Seo, Hoigi
Bang, Junseo
Lee, Haechang
Lee, Joohoon
Lee, Byung Hyun
Chun, Se Young
contents Text-to-image (T2I) models often suffer from text-image misalignment in complex scenes involving multiple objects and attributes. Semantic binding has attempted to associate the generated attributes and objects with their corresponding noun phrases (NPs) by text or latent optimizations with the modulation of cross-attention (CA) maps; yet, the factors that influence semantic binding remain underexplored. Here, we investigate the geometrical properties of text token embeddings and their CA maps. We found that the geometrical properties of token embeddings, specifically angular distances and norms, are crucial factors in the differentiation of the CA map. These theoretical findings led to our proposed training-free text-embedding-aware T2I framework, dubbed \textbf{TokeBi}, for strong semantic binding. TokeBi consists of Causality-Aware Projection-Out (CAPO) for distinguishing inter-NP CA maps and Adaptive Token Mixing (ATM) for enhancing inter-NP separation while maintaining intra-NP cohesion in CA maps. Extensive experiments confirm that TokeBi outperforms prior arts across diverse baselines and datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23011
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation
Seo, Hoigi
Bang, Junseo
Lee, Haechang
Lee, Joohoon
Lee, Byung Hyun
Chun, Se Young
Computer Vision and Pattern Recognition
Artificial Intelligence
Text-to-image (T2I) models often suffer from text-image misalignment in complex scenes involving multiple objects and attributes. Semantic binding has attempted to associate the generated attributes and objects with their corresponding noun phrases (NPs) by text or latent optimizations with the modulation of cross-attention (CA) maps; yet, the factors that influence semantic binding remain underexplored. Here, we investigate the geometrical properties of text token embeddings and their CA maps. We found that the geometrical properties of token embeddings, specifically angular distances and norms, are crucial factors in the differentiation of the CA map. These theoretical findings led to our proposed training-free text-embedding-aware T2I framework, dubbed \textbf{TokeBi}, for strong semantic binding. TokeBi consists of Causality-Aware Projection-Out (CAPO) for distinguishing inter-NP CA maps and Adaptive Token Mixing (ATM) for enhancing inter-NP separation while maintaining intra-NP cohesion in CA maps. Extensive experiments confirm that TokeBi outperforms prior arts across diverse baselines and datasets.
title Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.23011