为SAM模型提供快速高效的不确定性量化方法
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
- 基于贝叶斯熵构建兼顾多种不确定性的量化模型
- 在多个数据集上优于现有方法，计算开销小
- 适合需要可靠预测置信度的交互式或半监督场景
Segment Anything Model（SAM）的出现推动了众多语义分割应用的发展。对于某些任务，量化SAM的不确定性尤为重要。然而，类无关的基础模型SAM的模糊性给当前不确定性量化（UQ）方法带来挑战。本文提出一种基于贝叶斯熵公式的理论驱动不确定性量化模型，联合考虑随机性、认知性和新提出的任务不确定性。利用该公式训练出USAM——一种轻量级后处理UQ方法。我们的模型将不确定性根源追溯至参数不足、提示信息不足或图像模糊。所提出的确定性USAM在SA-V、MOSE、ADE20k、DAVIS和COCO数据集上展现出优越的预测能力，提供了一种计算成本低、易于使用的UQ替代方案，可用于支持用户提示、增强半监督流程，或平衡准确率与成本效率之间的权衡。
原文摘要 · Abstract (English)
The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of particular interest. However, the ambiguous nature of the class-agnostic foundation model SAM challenges current uncertainty quantification (UQ) approaches. This paper presents a theoretically motivated uncertainty quantification model based on a Bayesian entropy formulation jointly respecting aleatoric, epistemic, and the newly introduced task uncertainty. We use this formulation to train USAM, a lightweight post-hoc UQ method. Our model traces the root of uncertainty back to under-parameterised models, insufficient prompts or image ambiguities. Our proposed deterministic USAM demonstrates superior predictive capabilities on the SA-V, MOSE, ADE20k, DAVIS, and COCO datasets, offering a computationally cheap and easy-to-use UQ alternative that can support user-prompting, enhance semi-supervised pipelines, or balance the tradeoff between accuracy and cost efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。