ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models

• URL: http://arxiv.org/abs/2506.09740v1
• Date: Wed, 11 Jun 2025 13:47:03 GMT
• Title: ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models
• Authors: Qin Zhou, Zhiyang Zhang, Jinglong Wang, Xiaobin Li, Jing Zhang, Qian Yu, Lu Sheng, Dong Xu,
• Abstract summary: We propose a new method to calibrate pixel-text alignment in diffusion models based on the evidence lower bound (ELBO) of likelihood.<n>Our method is training-free and generic, eliminating the need to identify the specific cause of misalignment.
• Score: 46.27725105097827
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Diffusion models excel at image generation. Recent studies have shown that these models not only generate high-quality images but also encode text-image alignment information through attention maps or loss functions. This information is valuable for various downstream tasks, including segmentation, text-guided image editing, and compositional image generation. However, current methods heavily rely on the assumption of perfect text-image alignment in diffusion models, which is not the case. In this paper, we propose using zero-shot referring image segmentation as a proxy task to evaluate the pixel-level image and class-level text alignment of popular diffusion models. We conduct an in-depth analysis of pixel-text misalignment in diffusion models from the perspective of training data bias. We find that misalignment occurs in images with small sized, occluded, or rare object classes. Therefore, we propose ELBO-T2IAlign, a simple yet effective method to calibrate pixel-text alignment in diffusion models based on the evidence lower bound (ELBO) of likelihood. Our method is training-free and generic, eliminating the need to identify the specific cause of misalignment and works well across various diffusion model architectures. Extensive experiments on commonly used benchmark datasets on image segmentation and generation have verified the effectiveness of our proposed calibration approach.

Related papers

• Debiasing Vison-Language Models with Text-Only Training [15.069736314663352]
  We propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases. To address the limitations, we propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases.
  arXiv  Detail & Related papers  (2024-10-12T04:34:46Z)
• Removing Distributional Discrepancies in Captions Improves Image-Text Alignment [76.31530836622694]
  We introduce a model designed to improve the prediction of image-text alignment. Our approach focuses on generating high-quality training datasets for the alignment task. We also demonstrate the applicability of our model by ranking the images generated by text-to-image models based on text alignment.
  arXiv  Detail & Related papers  (2024-10-01T17:50:17Z)
• UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models [25.219960711604728]
  This paper proposes a novel approach for text image generation, utilizing a pre-trained diffusion model. Our approach involves the design and training of a light-weight character-level text encoder, which replaces the original CLIP encoder. By employing an inference stage refinement process, we achieve a notably high sequence accuracy when synthesizing text in arbitrarily given images.
  arXiv  Detail & Related papers  (2023-12-08T07:47:46Z)
• Fair Text-to-Image Diffusion via Fair Mapping [32.02815667307623]
  We propose a flexible, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image diffusion model. By effectively addressing the issue of implicit language bias, our method produces more fair and diverse image outputs.
  arXiv  Detail & Related papers  (2023-11-29T15:02:01Z)
• DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability [75.9781362556431]
  We propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. We show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks.
  arXiv  Detail & Related papers  (2023-08-18T05:03:48Z)
• Zero-shot spatial layout conditioning for text-to-image diffusion models [52.24744018240424]
  Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling. We consider image generation from text associated with segments on the image canvas, which combines an intuitive natural language interface with precise spatial control over the generated content. We propose ZestGuide, a zero-shot segmentation guidance approach that can be plugged into pre-trained text-to-image diffusion models.
  arXiv  Detail & Related papers  (2023-06-23T19:24:48Z)
• Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners [88.07317175639226]
  We propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainly uses the cross-attention score of a Stable Diffusion model to capture the mutual influence between visual and textual information.
  arXiv  Detail & Related papers  (2023-05-18T05:41:36Z)
• Discriminative Class Tokens for Text-to-Image Diffusion Models [102.88033622546251]
  We propose a non-invasive fine-tuning technique that capitalizes on the expressive potential of free-form text.<n>Our method is fast compared to prior fine-tuning methods and does not require a collection of in-class images.<n>We evaluate our method extensively, showing that the generated images are: (i) more accurate and of higher quality than standard diffusion models, (ii) can be used to augment training data in a low-resource setting, and (iii) reveal information about the data used to train the guiding classifier.
  arXiv  Detail & Related papers  (2023-03-30T05:25:20Z)
• Data Generation using Texture Co-occurrence and Spatial Self-Similarity for Debiasing [6.976822832216875]
  We propose a novel de-biasing approach that explicitly generates additional images using texture representations of oppositely labeled images. Every new generated image contains similar spatial information from a source image while transferring textures from a target image of opposite label. Our model integrates a texture co-occurrence loss that determines whether a generated image's texture is similar to that of the target, and a spatial self-similarity loss that determines whether the spatial details between the generated and source images are well preserved.
  arXiv  Detail & Related papers  (2021-10-15T08:04:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.