证据深度部分标签学习：量化消歧不确定性
Evidential Deep Partial Label Learning to Quantify Disambiguation Uncertainty
把证据建模（Dirichlet 分布上的 belief/credibility）引入弱监督标签消歧，为视觉分类任务提供可复用的不确定性量化头，可直接替换 softmax 输出用于噪声标注下的可靠性预测。
原文依据 we extend the evidence modeling mechanism to PLL, treating the candidate label set as the source of evidence for the label hypothesis
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论部分标签学习（PLL）是一种弱监督学习范式，其中每个实例被赋予一组候选标签，且仅有一个为真。然而，由于标注可能不准确，现有 PLL 算法通过最小化预测损失来进行标签消歧，导致模型对自身预测的可信度缺乏感知。为解决该问题，本文提出证据深度部分标签学习（ED-PLL）以量化消歧不确定性，旨在同时实现候选标签消歧与可靠性预测。首先，我们将证据建模机制扩展到 PLL，把候选标签集视为标签假设的证据来源，并利用信任度与可信度对分类不确定性建模，从而引导更可靠的消歧过程。同时，我们提出非候选标签在狄利克雷分布下的期望计算，通过一致性正则化抑制非候选标签的输出，进一步提升消歧准确性。此外，提出冲突感知正则化来评估冲突程度，它结合预测结果分布差异与模型不确定性来衡量类内实例间的一致性，从而提高模型的鲁棒性。另外，本文从期望最大化（EM）算法角度对方法进行了理论分析，且 ED-PLL 与任意深度网络或随机优化器兼容。在基准数据集与真实数据集上的实验验证了所提算法的有效性。
英文原文摘要 1663 字符
Partial label learning (PLL) is a weakly supervised learning, where each instance is assigned a set of candidate labels and only one is true. However, due to potentially inaccurate annotations, existing PLL algorithms disambiguate labeling by minimizing the prediction loss, which leaves the model unaware of its prediction credibility. To address this issue, this paper proposes the evidential deep partial label learning (ED-PLL) to quantify disambiguation uncertainty, aiming to achieve candidate label disambiguation and reliability prediction. Firstly, we extend the evidence modeling mechanism to PLL, treating the candidate label set as the source of evidence for the label hypothesis, and using belief and credibility to model classification uncertainty, thereby guiding a more reliable disambiguation process. Meanwhile, we propose the expectation calculation under the Dirichlet distribution of non-candidate labels, which suppresses the output of non-candidate labels by using consistency regularization to further improve the accuracy of disambiguation. Furthermore, a conflict-aware regularization is proposed to evaluate the degree of conflict, which measures the consistency between instances within the class by combining the differences in the distribution of prediction results and model uncertainty, and thus improves the robustness of the model. In addition, this paper theoretically analyzes our method from the perspective of the Expectation-Maximization (EM) algorithm, and the ED-PLL is compatible with any deep network or stochastic optimizer. Experiments on benchmark and real datasets verify the effectiveness of the proposed algorithm.