Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models

Text-to-image diffusion models have shown great success in generating high-quality text-guided images. Yet, these models may still fail to semantically align generated images with the provided text prompts, leading to problems like incorrect attribute binding and/or catastrophic object neglect. Give...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhang, Yasi, Yu, Peiyu, Ying Nian Wu
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.10.2024
Subjects
Alignment
Binding
Image enhancement
Image quality
Online AccessGet full text

Cover

More Information
Summary:Text-to-image diffusion models have shown great success in generating high-quality text-guided images. Yet, these models may still fail to semantically align generated images with the provided text prompts, leading to problems like incorrect attribute binding and/or catastrophic object neglect. Given the pervasive object-oriented structure underlying text prompts, we introduce a novel object-conditioned Energy-Based Attention Map Alignment (EBAMA) method to address the aforementioned problems. We show that an object-centric attribute binding loss naturally emerges by approximately maximizing the log-likelihood of a \(z\)-parameterized energy-based model with the help of the negative sampling technique. We further propose an object-centric intensity regularizer to prevent excessive shifts of objects attention towards their attributes. Extensive qualitative and quantitative experiments, including human evaluation, on several challenging benchmarks demonstrate the superior performance of our method over previous strong counterparts. With better aligned attention maps, our approach shows great promise in further enhancing the text-controlled image editing ability of diffusion models.
ISSN:2331-8422