面向计算机视觉的知识增强贝叶斯深度学习
Towards Knowledge-augmented Bayesian Deep Learning For Computer Vision
提供了一种将领域知识作为信息先验和自适应似然注入贝叶斯深度学习的两阶段框架，可提升视觉模型在分布偏移下的鲁棒性和不确定性估计质量。
原文依据 we propose a knowledge-augmented BDL framework that integrates domain knowledge both as an informative prior and as an adaptive likelihood
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论贝叶斯深度学习（BDL）将贝叶斯推理与深度学习相结合，在提升预测性能的同时实现有原则的不确定性量化。然而，现有的BDL方法通常依赖无信息的随机先验，限制了贝叶斯推理的优势。相比之下，知识增强深度学习在训练过程中显式注入领域知识，但缺乏概率基础。本文提出了一种知识增强的BDL框架，在统一的两阶段混合公式下，将领域知识同时作为信息先验和自适应似然进行整合。在第一阶段，我们通过预训练模型满足领域特定约束来学习知识引导的先验 p(θ|K)。在第二阶段，我们利用自适应知识似然 p(K|θ,D) 对任务数据进行贝叶斯推理，该似然在优化过程中动态地强制执行这些约束。这一统一框架使知识能够同时指导初始化和训练，显著提高了预测准确性、鲁棒性、适应性和不确定性估计。在半合成和真实知识场景下的多种计算机视觉任务实验表明，我们的两阶段框架始终优于最优的贝叶斯和知识增强基线。
英文原文摘要 1379 字符
Bayesian deep learning (BDL) integrates Bayesian inference with deep learning, improving predictive performance while enabling principled uncertainty quantification. However, existing BDLs often rely on non-informative random priors, limiting the benefits of Bayesian inference. In contrast, knowledge-augmented deep learning explicitly injects domain knowledge during training, yet lacks a probabilistic foundation. In this paper, we propose a knowledge-augmented BDL framework that integrates domain knowledge both as an informative prior and as an adaptive likelihood under a unified two-stage hybrid formulation. In the first stage, we learn a knowledge-informed prior p(\theta \mid \mathcal K ) by pre-training a model to satisfy domain-specific constraints. In the second stage, we perform Bayesian inference on task data with an adaptive knowledge likelihood p(\mathcal K \mid \theta, \mathcal D ), which dynamically enforces these constraints during optimization. This unified framework enables knowledge to guide both initialization and training, significantly improving prediction accuracy, robustness, adaptation and uncertainty estimation. Experiments on various computer vision tasks, including semi-synthetic and real-knowledge scenarios, demonstrate that our two-stage framework consistently outperforms state-of-the-art Bayesian and knowledge-augmented baselines.