补偿跨域文化遗产检索中稀缺历史图像：使用合成老化方法
Compensating for Scarce Historical Images in Cross-Domain Cultural Heritage Retrieval Using Synthetic Aging
- Nicolaus Copernicus University（尼古拉斯·哥白尼大学）
- Warsaw University of Technology（华沙理工大学）
- Clemens（克莱门斯公司）
- Czestochowa University of Technology（琴斯托霍瓦理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出用合成老化图像补充稀缺历史数据，在跨域文化遗产检索中，混合训练在低覆盖率下显著提升R@1，验证了真实与合成数据的互补性。
AI中文摘要：
文化遗产收藏品中通常包含同一物理对象的当代和历史视觉记录。由于对应图像可能在视角、采集条件、色彩还原、构图、分辨率和退化程度等方面存在差异，且真实历史图像常常稀缺，因此将这些记录关联起来十分困难。本研究探讨了合成老化的当代图像是否可以在双向实例级检索中替代或补充缺失的历史训练数据。通过面向退化的变换生成合成旧域图像。在三个数据集分区和三个训练种子上，对EfficientNetV2-M模型进行了身份不相交的训练、验证和测试集评估。将混合真实-合成训练与仅真实基线进行比较，采用按比例缩放和固定每轮300批次的调度。完全替换真实历史图像使双向平均R@1从86.56%降至81.27%，表明合成老化无法完全再现真实旧域的全部变异性。增加独立生成的合成变体数量未带来一致的改进。然而，在受控稀缺条件下，相对于按比例缩放的仅真实基线，合成补充在25%真实历史覆盖率下将平均R@1提高了3.69个百分点，在50%覆盖率下提高了2.92个百分点。在75%覆盖率下，增益降至2.00个百分点，而性能仍与完全真实数据参考相当。固定调度的仅真实对照组未再现这些改进。结果表明，真实和合成观测具有互补性。合成补充主要通过扩展跨域身份覆盖范围而非增加训练曝光来有益于检索，其贡献随着真实历史覆盖率的增加而逐渐减少。
英文摘要：
Cultural heritage collections often contain contemporary and historical visual records of the same physical object. Linking these records is difficult because corresponding images may differ in viewpoint, acquisition conditions, color reproduction, framing, resolution, and degradation, while genuine historical images are frequently scarce. This study investigates whether synthetically aged contemporary images can replace or complement missing historical training data in bidirectional instance-level retrieval. Synthetic old-domain images are generated using degradation-oriented transformations. An EfficientNetV2-M model is evaluated on identity-disjoint training, validation, and test sets across three dataset partitions and three training seeds. Mixed real-synthetic training is compared with real-only baselines using proportionally scaled and fixed 300-batch-per-epoch schedules. Complete replacement of genuine historical images reduced bidirectional mean R@1 from 86.56% to 81.27%, showing that synthetic aging does not reproduce the full genuine old-domain variability. Increasing the number of independently generated synthetic variants provided no consistent improvement. Under controlled scarcity, however, synthetic completion improved mean R@1 by 3.69 percentage points at 25% genuine historical coverage and by 2.92 points at 50%, relative to the proportionally scaled real-only baselines. At 75%, the gain decreased to 2.00 points, while performance remained comparable to the complete-real-data reference. Fixed-schedule real-only controls did not reproduce these improvements. The results indicate that genuine and synthetic observations are complementary. Synthetic completion primarily benefits retrieval by extending cross-domain identity coverage rather than by increasing training exposure, with its contribution gradually decreasing as genuine historical coverage increases.
