从 Softmax 到 Dirichlet：面向半监督语义分割的证据学习
From Softmax to Dirichlet: Evidential Learning for Semi-supervised Semantic Segmentation
用狄利克雷分布对类别概率建模，从分布视角给出原则性的不确定性估计，替代 softmax 置信度做伪标签筛选；HESS 将排他证据与集体证据解耦，可直接嵌入现有半监督分割框架提升伪标签可靠性。
原文依据 we propose a novel evidential learning framework to explicitly model the prediction uncertainty for reliable pseudo-label selection
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论半监督语义分割的关键挑战在于如何充分利用大量无标注数据，以提升模型的泛化性能、实现鲁棒分割。然而，现有基于 softmax 分数的筛选方法往往受神经网络过自信问题的影响，导致错误的伪标签被纳入，进而对训练过程产生负面影响。本文提出一种新的证据学习框架，显式建模预测不确定性，以实现可靠的伪标签选择。通过使用狄利克雷分布对类别概率的分布建模，我们从分布视角获得了有原则且更优的不确定性估计。此外，我们提出 HESS（Hyper-ESS），将排他证据与集体证据的建模解耦，以实现全面的证据感知，从而得到更准确的不确定性估计。在三个具有挑战性的基准上的大量实验表明，将 HESS 集成到现有的半监督语义分割框架中能够持续提升性能，这得益于更可靠的伪标签选择。本工作揭示了证据学习在半监督语义分割中的潜力，并为未来研究开辟了新的方向。
英文原文摘要 1320 字符
The critical challenge of semi-supervised semantic segmentation lies in how to fully exploit a large volume of unlabeled data to improve the model's generalization performance for robust segmentation. However, existing softmax scores-based filtering methods tend to be affected by the overconfidence issue in neural networks, leading to the inclusion of incorrect pseudo-labels that negatively impact the training process. In this paper, we propose a novel evidential learning framework to explicitly model the prediction uncertainty for reliable pseudo-label selection. By modeling the distribution of class probabilities using Dirichlet distributions, we obtain principled and improved uncertainty estimates from a distributional perspective. Furthermore, we propose HESS (Hyper-ESS), decoupling the modeling of exclusive and collective evidence for comprehensive evidence perception, to yield more accurate uncertainty estimates. Extensive experiments on three challenging benchmarks demonstrate that integrating HESS into existing semi-supervised semantic segmentation frameworks consistently improves performance, benefiting from more reliable pseudo-label selection. Our work sheds light on the potential of evidential learning in semi-supervised semantic segmentation and opens up new avenues for future research.