通过考虑不确定性提升像素级异常检测准确率
Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection
- 用证据分类器结合似然比检验区分已知与未知像素特征
- 在5个基准数据集上实现2.5%最低误报率，90.91%高精确率
- 适合自动驾驶等复杂场景中未知物体识别任务
在真实自动驾驶场景中，基于已知类别训练的语义分割模型常会自信地错误分类未知物体。虽然像素级分布外检测可识别未知物体，但在复杂场景下，罕见类别常被误判为真正未知。本文提出一种不确定性感知的似然比估计方法，利用证据分类器结合似然比检验，从语义分割模型中区分已知与未知像素特征，并显式建模不确定性。该方法不输出点估计，而是生成概率分布，同时捕捉稀有训练样本和不完美合成异常带来的不确定性。通过有效利用不确定性，可更充分地发挥异常暴露（outlier exposure）的作用。在五个标准基准数据集上评估，本方法在现有技术中实现了最低的平均误报率（2.5%），同时保持了90.91%的高平均精确率，计算开销几乎可忽略。代码已开源于 https://github.com/glasbruch/ULRE。
原文摘要 · Abstract (English)
Semantic segmentation models trained on known object classes often fail in real-world autonomous driving scenarios by confidently misclassifying unknown objects. While pixel-wise out-of-distribution detection can identify unknown objects, existing methods struggle in complex scenes where rare object classes are often confused with truly unknown objects. We introduce an uncertainty-aware likelihood ratio estimation method that addresses these limitations. Our approach uses an evidential classifier within a likelihood ratio test to distinguish between known and unknown pixel features from a semantic segmentation model, while explicitly accounting for uncertainty. Instead of producing point estimates, our method outputs probability distributions that capture uncertainty from both rare training examples and imperfect synthetic outliers. We show that by incorporating uncertainty in this way, outlier exposure can be leveraged more effectively. Evaluated on five standard benchmark datasets, our method achieves the lowest average false positive rate (2.5%) among state-of-the-art while maintaining high average precision (90.91%) and incurring only negligible computational overhead. Code is available at https://github.com/glasbruch/ULRE.
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。