提升异常分割精度，让模型更准识别障碍物边界和异常区域。
Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precision
- 利用物体先验信息校准异常得分，避免内部不一致
- 边界精细化处理使像素级准确率高达96.99，误报率降至0.07
- 适合自动驾驶等对安全要求高的实际场景
无监督异常分割在自动驾驶等安全敏感应用中至关重要。现有基于掩码的方法常存在边界模糊、物体内部异常评分不一致及背景噪声误检问题。本文提出Objectomaly，一种基于物体感知的精修框架，包含三阶段：(1) 使用现有OoD骨干网络进行粗粒度异常打分；(2) 利用SAM生成的实例掩码，对物体级别异常得分进行归一化校准；(3) 通过拉普拉斯滤波与高斯平滑实现轮廓精细优化。在SMIYC AnomalyTrack/ObstacleTrack和RoadAnomaly等关键基准上达到领先性能，像素级指标AuPRC最高达96.99，FPR$_{95}$低至0.07，组件级F1$-$score最高达83.44。消融实验与真实驾驶视频的定性结果验证了方法的鲁棒性与泛化能力。代码将在发表后公开。
原文摘要 · Abstract (English)
Out-of-Distribution (OoD) segmentation is critical for safety-sensitive applications like autonomous driving. However, existing mask-based methods often suffer from boundary imprecision, inconsistent anomaly scores within objects, and false positives from background noise. We propose \textbf{\textit{Objectomaly}}, an objectness-aware refinement framework that incorporates object-level priors. Objectomaly consists of three stages: (1) Coarse Anomaly Scoring (CAS) using an existing OoD backbone, (2) Objectness-Aware Score Calibration (OASC) leveraging SAM-generated instance masks for object-level score normalization, and (3) Meticulous Boundary Precision (MBP) applying Laplacian filtering and Gaussian smoothing for contour refinement. Objectomaly achieves state-of-the-art performance on key OoD segmentation benchmarks, including SMIYC AnomalyTrack/ObstacleTrack and RoadAnomaly, improving both pixel-level (AuPRC up to 96.99, FPR$_{95}$ down to 0.07) and component-level (F1$-$score up to 83.44) metrics. Ablation studies and qualitative results on real-world driving videos further validate the robustness and generalizability of our method. Code will be released upon publication.
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。