Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methods

TL;DR

This paper explores training-free methods to improve sample diversity in segmentation diffusion models for wildfire spread prediction, medical imaging, and urban scene understanding, achieving higher accuracy with less computational effort.

Contribution

It adapts existing diversity techniques to segmentation tasks and introduces a new clustering method, enhancing sample efficiency and diversity in diffusion-based segmentation models.

Findings

Up to 7.5% improvement in HM IoU on wildfire dataset

Up to 16.4% improvement on Cityscapes dataset

Training-free methods increase diversity with minimal additional cost

Abstract

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