Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
Uncertainty quantification in text-to-image (T2I) generative models is crucial for understanding model behavior and improving output reliability. In this paper, we are the first to quantify and evaluate the uncertainty of T2I models with respect to the prompt. Alongside adapting existing approaches designed to measure uncertainty in the image space, we also introduce Prompt-based UNCertainty Estimation for T2I models (PUNC), a novel method leveraging Large Vision-Language Models (LVLMs) to better address uncertainties arising from the semantics of the prompt and generated images. PUNC utilizes a LVLM to caption a generated image, and then compares the caption with the original prompt in the more semantically meaningful text space. PUNC also enables the disentanglement of both aleatoric and epistemic uncertainties via precision and recall, which image-space approaches are unable to do. Extensive experiments demonstrate that PUNC outperforms state-of-the-art uncertainty estimation techniques across various settings. Uncertainty quantification in text-to-image generation models can be used on various applications including bias detection, copyright protection, and OOD detection. We also introduce a comprehensive dataset of text prompts and generation pairs to foster further research in uncertainty quantification for generative models. Our findings illustrate that PUNC not only achieves competitive performance but also enables novel applications in evaluating and improving the trustworthiness of text-to-image models.
Code (0)
등록된 구현이 없습니다.
Tasks
Bias DetectionDisentanglementImage GenerationText to Image GenerationText-to-Image GenerationUncertainty QuantificationSimilar Papers 제목 키워드 기반
Quantifying and Understanding Uncertainty in Large Reasoning Models
Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional methods are often insufficient because they…
Answer GenerationConformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation
Scene Graph Generation (SGG) aims to represent visual scenes by identifying objects and their pairwise relationships, providing a structured understanding of image content. However, inherent challenges like long-tailed c…
Conformal PredictionGraph GenerationPredictionScene Graph Generation+1Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation
Deep learning based methods for automatic organ segmentation have shown promise in aiding diagnosis and treatment planning. However, quantifying and understanding the uncertainty associated with model predictions is cruc…
BenchmarkingMedical Image AnalysisOrgan SegmentationOut-of-Distribution Detection+2Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering
Large language models (LLMs) have shown strong capabilities, enabling concise, context-aware answers in question answering (QA) tasks. The lack of transparency in complex LLMs has inspired extensive research aimed at dev…
Question AnsweringCue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
Humans and traditional computer vision methods rely on a diverse set of monocular cues to infer 3D structure from a single image, such as shading, texture, silhouette, etc. While recent deep generative models have dramat…
3D Generation