通过量化不确定性提升分割模型在未知场景下的鲁棒性
Towards Integrating Uncertainty for Domain-Agnostic Segmentation
- 构建了包含8个挑战数据集的UncertSAM基准测试
- 最后一层拉普拉斯近似能有效预测分割错误
- 适合关注模型可靠性与泛化能力的研究者
如分割一切模型（SAM）这类基础分割模型具备出色的零样本性能，但在分布外或知识有限的场景下仍易出错。本文探究不确定性量化是否可缓解此类问题并提升模型在无领域依赖场景下的泛化能力。为此，我们（1）构建了包含8个数据集的UncertSAM基准，涵盖阴影、透明、伪装等挑战性条件；（2）评估多种轻量级后处理不确定性估计方法；（3）初步测试基于不确定性的预测优化步骤。结果表明，最后一层拉普拉斯近似生成的不确定性估计与分割误差高度相关，具有实际意义。尽管优化效果尚处初期，但研究证实引入不确定性有助于实现更稳健的跨域分割。相关数据集与代码已公开。
原文摘要 · Abstract (English)
Foundation models for segmentation such as the Segment Anything Model (SAM) family exhibit strong zero-shot performance, but remain vulnerable in shifted or limited-knowledge domains. This work investigates whether uncertainty quantification can mitigate such challenges and enhance model generalisability in a domain-agnostic manner. To this end, we (1) curate UncertSAM, a benchmark comprising eight datasets designed to stress-test SAM under challenging segmentation conditions including shadows, transparency, and camouflage; (2) evaluate a suite of lightweight, post-hoc uncertainty estimation methods; and (3) assess a preliminary uncertainty-guided prediction refinement step. Among evaluated approaches, a last-layer Laplace approximation yields uncertainty estimates that correlate well with segmentation errors, indicating a meaningful signal. While refinement benefits are preliminary, our findings underscore the potential of incorporating uncertainty into segmentation models to support robust, domain-agnostic performance. Our benchmark and code are made publicly available.
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。