Hallucination Early Detection in Diffusion Models

• URL: http://arxiv.org/abs/2604.20354v1
• Date: Wed, 22 Apr 2026 08:57:19 GMT
• Title: Hallucination Early Detection in Diffusion Models
• Abstract summary: We introduce HEaD+ (Hallucination Early Detection +), a novel approach designed to identify incorrect generations early in the diffusion process.<n>HEaD+ is trained on the newly created InsideGen dataset of 45,000 generated images, each containing prompts with up to seven objects.<n>Our findings demonstrate a 6-8% increase in the likelihood of achieving a complete generation with four objects when applying HEaD+ alongside existing models.
• Score: 84.67602765567086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-Image generation has seen significant advancements in output realism with the advent of diffusion models. However, diffusion models encounter difficulties when tasked with generating multiple objects, frequently resulting in hallucinations where certain entities are omitted. While existing solutions typically focus on optimizing latent representations within diffusion models, the relevance of the initial generation seed is typically underestimated. While using various seeds in multiple iterations can improve results, this method also significantly increases time and energy costs. To address this challenge, we introduce HEaD+ (Hallucination Early Detection +), a novel approach designed to identify incorrect generations early in the diffusion process. The HEaD+ framework integrates cross-attention maps and textual information with a novel input, the Predicted Final Image. The objective is to assess whether to proceed with the current generation or restart it with a different seed, thereby exploring multiple-generation seeds while conserving time. HEaD+ is trained on the newly created InsideGen dataset of 45,000 generated images, each containing prompts with up to seven objects. Our findings demonstrate a 6-8% increase in the likelihood of achieving a complete generation (i.e., an image accurately representing all specified subjects) with four objects when applying HEaD+ alongside existing models. Additionally, HEaD+ reduces generation times by up to 32% when aiming for a complete image, enhancing the efficiency of generating complete and accurate object representations relative to leading models. Moreover, we propose an integrated localization module that predicts object centroid positions and verifies pairwise spatial relations (if requested by the users) at an intermediate timestep, gating generation together with object presence to further improve relation-consistent outcomes.

Related papers

• Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI [11.267487718542442]
  In medical imaging, generative models are increasingly relied upon for two distinct but equally critical tasks.<n>Generation seeks high perceptual quality and diversity, while reconstruction focuses on data fidelity and faithfulness.<n>In this work, we introduce a "generative model zoo" and analyze how modern latent diffusion models and autoregressive models navigate the reconstruction-generation spectrum.
  arXiv  Detail & Related papers  (2025-07-25T11:53:50Z)
• StateSpaceDiffuser: Bringing Long Context to Diffusion World Models [52.92249035412797]
  We introduce StateSpaceDiffuser, where a diffusion model is enabled to perform long-context tasks by integrating features from a state-space model.<n>This design restores long-term memory while preserving the high-fidelity synthesis of diffusion models.
  arXiv  Detail & Related papers  (2025-05-28T11:27:54Z)
• GAS: Generative Avatar Synthesis from a Single Image [54.95198111659466]
  We present a framework for synthesizing view-consistent and temporally coherent avatars from a single image.<n>Our approach combines the reconstruction power of regression-based 3D human reconstruction with the generative capabilities of a diffusion model.
  arXiv  Detail & Related papers  (2025-02-10T19:00:39Z)
• BudgetFusion: Perceptually-Guided Adaptive Diffusion Models [15.293203074854267]
  We present BudgetFusion, a novel model that suggests the most perceptually efficient number of diffusion steps before a diffusion model starts to generate an image.<n>Experiments show that BudgetFusion saves up to five seconds per prompt without compromising perceptual similarity.<n>We hope this work can initiate efforts toward answering a core question: how much do humans perceptually gain from images created by a generative model, per watt of energy?
  arXiv  Detail & Related papers  (2024-12-08T02:23:40Z)
• Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection [87.22082662250999]
  We introduce HEaD (Hallucination Early Detection), a new paradigm designed to swiftly detect incorrect generations at the beginning of the diffusion process. We demonstrate that using HEaD saves computational resources and accelerates the generation process to get a complete image. Our findings reveal that HEaD can save up to 12% of the generation time on a two objects scenario.
  arXiv  Detail & Related papers  (2024-09-16T18:00:00Z)
• Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities [88.398085358514]
  Contrastive Deepfake Embeddings (CoDE) is a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities.
  arXiv  Detail & Related papers  (2024-07-29T18:00:10Z)
• DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
  Current perceptive models heavily depend on resource-intensive datasets. We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability. Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
  arXiv  Detail & Related papers  (2024-03-20T04:58:03Z)
• Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors [56.82596340418697]
  We propose a simple yet effective framework comprising a pre-trained Stable Diffusion (SD) model containing rich generative priors, a unified head (U-head) capable of integrating hierarchical representations, and an adapted expert providing discriminative priors. Comprehensive investigations unveil potential characteristics of Vermouth, such as varying granularity of perception concealed in latent variables at distinct time steps and various U-net stages. The promising results demonstrate the potential of diffusion models as formidable learners, establishing their significance in furnishing informative and robust visual representations.
  arXiv  Detail & Related papers  (2024-01-29T10:36:57Z)
• Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction [60.52716381465063]
  We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images. Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality pseudo-observations. Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times.
  arXiv  Detail & Related papers  (2023-05-24T14:00:32Z)
• SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation [23.174391810184602]
  We propose a sequence-aware diffusion model (SADM) for the generation of longitudinal medical images. Our method extends this new technique by introducing a sequence-aware transformer as the conditional module in a diffusion model. Our experiments on 3D longitudinal medical images demonstrate the effectiveness of SADM compared with baselines and alternative methods.
  arXiv  Detail & Related papers  (2022-12-16T01:35:27Z)
• A Survey on Generative Diffusion Model [75.93774014861978]
  Diffusion models are an emerging class of deep generative models. They have certain limitations, including a time-consuming iterative generation process and confinement to high-dimensional Euclidean space. This survey presents a plethora of advanced techniques aimed at enhancing diffusion models.
  arXiv  Detail & Related papers  (2022-09-06T16:56:21Z)

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.