paper-with-me

Papers

Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds

2024-11-27 · Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann

Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin on the right of a bowl". Understanding these inconsistencies is crucial for reliable image generation. In this paper, we highlight the significant role of initial noise in these inconsistencies, where certain noise patterns are more reliable for compositional prompts than others. Our analyses reveal that different initial random seeds tend to guide the model to place objects in distinct image areas, potentially adhering to specific patterns of camera angles and image composition associated with the seed. To improve the model's compositional ability, we propose a method for mining these reliable cases, resulting in a curated training set of generated images without requiring any manual annotation. By fine-tuning text-to-image models on these generated images, we significantly enhance their compositional capabilities. For numerical composition, we observe relative increases of 29.3% and 19.5% for Stable Diffusion and PixArt-{\alpha}, respectively. Spatial composition sees even larger gains, with 60.7% for Stable Diffusion and 21.1% for PixArt-{\alpha}.

📄 PDF Abstract BibTeX arXiv:2411.18810

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples

2024-02-20 · Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee

We propose CounterCurate, a framework to comprehensively improve the visio-linguistic compositional reasoning capability for both contrastive and generative multimodal models. In particular, we identify two critical unde…

counterfactualData AugmentationImage GenerationText Generation

Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining

2023-11-07 · Ugur Sahin, Hang Li, Qadeer Khan, Daniel Cremers 외

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on …

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

2024-10-28 · CVPR 2025 1 · Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng 외

Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable i…

3D GenerationImage GenerationScene GenerationText to 3D

Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection

2024-07-21 · KwanYong Park, Kuniaki Saito, Donghyun Kim

Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approach…

Contrastive Learningobject-detectionObject DetectionSynthetic Data Generation

Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality

2026-06-11 · Wei Li, Zhen Huang, Xinmei Tian arxiv

Contrastively trained vision-language models like CLIP, have made remarkable progress in learning joint image-text representations, but still face challenges in compositional understanding. They often exhibit a "bag-of-w…

Text-to-Image Generation