Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.20188 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912976169074688 |
|---|---|
| author | Gerard, Sebastian Sullivan, Josephine |
| author_facet | Gerard, Sebastian Sullivan, Josephine |
| contents | Predicting future states in uncertain environments, such as wildfire spread, medical diagnosis, or autonomous driving, requires models that can consider multiple plausible outcomes. While diffusion models can effectively learn such multi-modal distributions, naively sampling from these models is computationally inefficient, potentially requiring hundreds of samples to find low-probability modes that may still be operationally relevant. In this work, we address the challenge of sample-efficient ambiguous segmentation by evaluating several training-free sampling methods that encourage diverse predictions. We adapt two techniques, particle guidance and SPELL, originally designed for the generation of diverse natural images, to discrete segmentation tasks, and additionally propose a simple clustering-based technique. We validate these approaches on the LIDC medical dataset, a modified version of the Cityscapes dataset, and MMFire, a new simulation-based wildfire spread dataset introduced in this paper. Compared to naive sampling, these approaches increase the HM IoU* metric by up to 7.5% on MMFire and 16.4% on Cityscapes, demonstrating that training-free methods can be used to efficiently increase the sample diversity of segmentation diffusion models with little cost to image quality and runtime.
Code and dataset: https://github.com/SebastianGer/wildfire-spread-scenarios |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20188 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methods Gerard, Sebastian Sullivan, Josephine Computer Vision and Pattern Recognition Predicting future states in uncertain environments, such as wildfire spread, medical diagnosis, or autonomous driving, requires models that can consider multiple plausible outcomes. While diffusion models can effectively learn such multi-modal distributions, naively sampling from these models is computationally inefficient, potentially requiring hundreds of samples to find low-probability modes that may still be operationally relevant. In this work, we address the challenge of sample-efficient ambiguous segmentation by evaluating several training-free sampling methods that encourage diverse predictions. We adapt two techniques, particle guidance and SPELL, originally designed for the generation of diverse natural images, to discrete segmentation tasks, and additionally propose a simple clustering-based technique. We validate these approaches on the LIDC medical dataset, a modified version of the Cityscapes dataset, and MMFire, a new simulation-based wildfire spread dataset introduced in this paper. Compared to naive sampling, these approaches increase the HM IoU* metric by up to 7.5% on MMFire and 16.4% on Cityscapes, demonstrating that training-free methods can be used to efficiently increase the sample diversity of segmentation diffusion models with little cost to image quality and runtime. Code and dataset: https://github.com/SebastianGer/wildfire-spread-scenarios |
| title | Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methods |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.20188 |