用软伪标签提升弱监督分割性能，效果超过全像素标注。
Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentation
- 引入软伪标签替代硬标签，更好表达分类不确定性
- 在仅用画线标注下，性能超越复杂专用模型
- 方法通用，适用于其他弱监督任务
本文研究弱监督图像分割问题，即仅部分像素有真实标签（画线标注）。提出一种基于软伪标签的自标注方法，通过优化标准无监督CRF/Potts损失的松弛形式来训练网络。相比传统硬伪标签，软伪标签能更准确表示类别不确定性和潜在错误。论文推导了一个合理的辅助损失函数，系统评估了多种CRF松弛方法（凸与非凸）、邻域系统及网络预测与软伪标签间的连接项。同时提出一种通用的连续子问题求解器。实验表明，仅使用标准网络架构，该方法在画线标注下表现优异，显著优于更复杂的专用弱监督系统，甚至可超越全像素精确标注的效果。核心思想可推广至其他弱监督学习场景。
原文摘要 · Abstract (English)
We consider weakly supervised segmentation where only a fraction of pixels have ground truth labels (scribbles) and focus on a self-labeling approach optimizing relaxations of the standard unsupervised CRF/Potts loss on unlabeled pixels. While WSSS methods can directly optimize such losses via gradient descent, prior work suggests that higher-order optimization can improve network training by introducing hidden pseudo-labels and powerful CRF sub-problem solvers, e.g. graph cut. However, previously used hard pseudo-labels can not represent class uncertainty or errors, which motivates soft self-labeling. We derive a principled auxiliary loss and systematically evaluate standard and new CRF relaxations (convex and non-convex), neighborhood systems, and terms connecting network predictions with soft pseudo-labels. We also propose a general continuous sub-problem solver. Using only standard architectures, soft self-labeling consistently improves scribble-based training and outperforms significantly more complex specialized WSSS systems. It can outperform full pixel-precise supervision. Our general ideas apply to other weakly-supervised problems/systems.
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。