提出单次前向传播的像素级分布外检测方法，兼顾精度与边缘部署效率。
Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
- 融合几何比与能量得分的混合指标，实现单次前向推理
- 在miniMUAD上达到0.8539的AUROC，优于各基线方法
- 适合需要实时性与鲁棒性的移动端语义分割场景
移动机器人可靠的语义分割需兼具高精度密集预测与分布偏移下的鲁棒不确定性估计。现有强基线如蒙特卡洛丢弃常需多次随机前向传播，难以部署于边缘平台。本文提出Energy-Aware NECO，一种针对语义分割的单次前向像素级分布外（OOD）检测方法。该方法结合解码器特征计算的中心化NECO型几何比与基于逻辑值的能量得分，二者均使用纯内分布验证集统计量标准化，并通过凸组合融合。在miniMUAD子集上使用真实像素级OOD标签进行评估，所提混合评分达到0.8539的AUROC，优于仅用NECO（0.8280）、仅用能量得分（0.8171）及集成预测熵基线（0.8124）。定性分析与工作点研究显示，该方法在保持单次前向优势的同时提升了整体排序性能。代码已公开于https://github.com/boyuan-zhangx/Energy-Aware_NECO。
原文摘要 · Abstract (English)
Reliable semantic segmentation for mobile robots requires both accurate dense prediction and robust uncertainty estimation under distribution shift. Strong uncertainty baselines such as Monte Carlo Dropout often require repeated stochastic forward passes and are difficult to deploy on edge platforms. We propose Energy-Aware NECO, a single-pass pixel-wise out-of-distribution (OOD) detector for semantic segmentation. The method combines a centered NECO-style geometric ratio computed from decoder features with a logit-based Energy score. Both components are standardized using statistics fitted on a pure in-distribution validation split and fused through a convex combination. We evaluate the method on the miniMUAD subset using true pixel-level OOD labels. The proposed hybrid score achieves an AUROC of 0.8539, outperforming NECO-only (0.8280), Energy-only (0.8171), and an ensemble predictive-entropy baseline (0.8124). Additional qualitative and operating-point analyses show that the hybrid detector improves overall ranking performance while preserving the efficiency advantages of a single-pass design. Code is available at https://github.com/boyuan-zhangx/Energy-Aware_NECO
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。