通过扰动检测稳定性，提升神经元胞自动机的预测可信度。
Measuring Prediction Uncertainty in Neural Cellular Automata
- 利用元胞自动机迭代特性，通过微小扰动测试预测稳定性。
- 在多个医学图像分割数据集上，识别失败案例准确率优于基线。
- 无需修改模型或重训练，适合临床部署中的可靠性评估。
神经元胞自动机（NCA）为编码器-解码器分割网络提供了轻量级替代方案，但难以判断预测是否可信。本文研究了不修改底层架构或重新训练模型的情况下，基于NCA的医学图像分割不确定性估计。受动力系统启发，将收敛吸引子视为高置信度预测。提出「韧性」（resilience）这一简单度量方法，通过在自动机状态施加微小扰动，探测最终预测的稳定性：返回相同结果的预测视为可信，显著变化的则标记为不确定。通过选择性预测指标（ΔDice@90 和 AURC）及排序指标（AUROC、AUPRC）评估不确定性有效性。在多个医学分割基准测试中，韧性比基线更可靠地识别出失败案例，提升了NCA模型的信任度与安全性。
原文摘要 · Abstract (English)
Neural cellular automata (NCA) provide a lightweight alternative to encoder-decoder segmentation networks. However, it can be difficult to decide when a prediction should be trusted. Here, we study uncertainty estimation for NCA-based medical image segmentation without modifying the underlying architecture or retraining the model. Our approach is motivated by viewing the NCA as a dynamical system where convergent attractors correspond to confident predictions. Concretely, we propose resilience, a simple measure that leverages the intrinsic iterative structure of NCAs by probing the stability of the final prediction under small perturbations of the automaton state. Predictions that return to the same solution are deemed confident, while those that change substantially are flagged as uncertain. We evaluate uncertainty by its ability to predict segmentation quality using selective prediction metrics ($Δ$Dice@90 and AURC) and ranking metrics (AUROC and AUPRC). Across multiple medical segmentation benchmarks, resilience identifies failure cases more reliably than baselines, improving trust and safety in NCA-based models.
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。