HierUQ：面向退化图像分类的自适应粒度协调分层不确定性量化
HierUQ: Hierarchical Uncertainty Quantification with Adaptive Granularity Reconciliation for Degraded Image Classification
针对低质量/退化图像，用基于标签平滑与 proper scoring rule 的分层不确定性量化，配合置信度不足时回退到高层节点的路径调整机制，可作为视觉模型在分布偏移下做可靠预测与拒识的通用手段。
原文依据 When confidence is insufficient, a Confidence-Aware Path Adjustment (CAPA) mechanism adaptively rolls back predictions to higher-level nodes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论退化图像上的分层分类（HC）因特征损坏、置信度估计不可靠以及细粒度误分类而面临挑战。现有方法在低质量视觉条件下往往难以兼顾语义一致性与自适应决策路径。为此，我们提出 HierUQ，一个将不确定性量化与自适应粒度协调相统一的框架。Vision Transformer 骨干网络提取全局特征，并通过双线性注意力与语义引导的交叉注意力与语义嵌入融合。我们基于标签平滑与 proper scoring rule 提出了一种有原则的分层不确定性量化（HUQ）策略。当置信度不足时，置信度感知路径调整（CAPA）机制会将预测自适应地回退到更高层节点，从而缓解过度分类与错误传播、稳定学习轨迹、克服退化带来的干扰并提升细粒度分类精度。为增强学习，我们引入了在多层级目标上带动态损失加权的自步联合优化（MLJO）。在退化遥感与自然图像基准上的实验表明，HierUQ 取得了最优性能，并具有强鲁棒性与适应性。
英文原文摘要 1339 字符
Hierarchical classification (HC) on degraded images presents challenges due to feature corruption, unreliable confidence estimation, and fine-grained misclassification. Existing methods often struggle to balance semantic consistency and adaptive decision paths under low-quality visual conditions. To address this, we propose HierUQ, a unified framework that integrates uncertainty quantification with adaptive granularity reconciliation. A Vision Transformer backbone extracts global features, which are fused with semantic embeddings via bilinear and semantic-guided cross-attentions. We develop a principled Hierarchical Uncertainty Quantification (HUQ) strategy based on label smoothing and proper scoring rules. When confidence is insufficient, a Confidence-Aware Path Adjustment (CAPA) mechanism adaptively rolls back predictions to higher-level nodes, mitigating overclassification and error propagation, stabilizing the learning trajectory, overcoming degradation-induced interference, and enhancing fine-grained classification accuracy. To enhance learning, we introduce a self-paced joint optimization (MLJO) over multi-level objectives with dynamic loss weighting. Experiments on degraded remote sensing and natural image benchmarks show that HierUQ achieves state-of-the-art performance with strong robustness and adaptability.