用不确定性与能量损失提升半监督语义分割精度
Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation
- 引入数据不确定性和能量损失机制，增强伪标签可靠性
- 在Cityscapes上达到82.1%的平均交并比，优于现有方法
- 适合需要减少标注成本的自动驾驶场景研究
半监督（SS）语义分割通过利用标注和未标注图像，缓解像素级标注耗时费力的问题。伪标签监督是训练网络的核心方法之一。本文在交并集伪监督网络中引入了数据不确定性（aleatoric uncertainty）和基于能量的建模。通过双预测分支建模数据内在噪声变化，网络输出的每像素方差参数可量化数据不确定性。此外，基于能量的损失将生成建模潜力应用于下游半监督分割任务。不确定性损失与能量损失分别与伪交集、伪并集及真实标签结合，在对应网络分支中使用。与当前最先进方法的对比分析显示，性能指标显著提升。
原文摘要 · Abstract (English)
Semi-supervised (SS) semantic segmentation exploits both labeled and unlabeled images to overcome tedious and costly pixel-level annotation problems. Pseudolabel supervision is one of the core approaches of training networks with both pseudo labels and ground-truth labels. This work uses aleatoric or data uncertainty and energy based modeling in intersection-union pseudo supervised network.The aleatoric uncertainty is modeling the inherent noise variations of the data in a network with two predictive branches. The per-pixel variance parameter obtained from the network gives a quantitative idea about the data uncertainty. Moreover, energy-based loss realizes the potential of generative modeling on the downstream SS segmentation task. The aleatoric and energy loss are applied in conjunction with pseudo-intersection labels, pseudo-union labels, and ground-truth on the respective network branch. The comparative analysis with state-of-the-art methods has shown improvement in performance metrics.
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。