This paper introduces SAGHOG, a self-supervised pretraining strategy for
writer retrieval using HOG features of the binarized input image. Our
preprocessing involves the application of the Segment Anything technique to
extract handwriting from various datasets, ending up with about 24k documents,
followed by training a vision transformer on reconstructing masked patches of
the handwriting. SAGHOG is then finetuned by appending NetRVLAD as an encoding
layer to the pretrained encoder. Evaluation of our approach on three historical
datasets, Historical-WI, HisFrag20, and GRK-Papyri, demonstrates the
effectiveness of SAGHOG for writer retrieval. Additionally, we provide ablation
studies on our architecture and evaluate un- and supervised finetuning.
Notably, on HisFrag20, SAGHOG outperforms related work with a mAP of 57.2 % - a
margin of 11.6 % to the current state of the art, showcasing its robustness on
challenging data, and is competitive on even small datasets, e.g. GRK-Papyri,
where we achieve a Top-1 accuracy of 58.0%.

介绍了 SAGHOG，一种使用二值化输入图像的 HOG 特征进行自监督预训练的书写者检索策略。通过应用 'Segment Anything' 技术从各种数据集中提取手写文本，利用预训练的视觉转换器对手写文本的掩码补丁进行重构来进行预处理。然后，通过在预训练编码器后附加 NetRVLAD 编码层对 SAGHOG 进行微调。在三个历史数据集 Historical-WI、HisFrag20 和 GRK-Papyri 上评估了我们的方法，证明了 SAGHOG 在书写者检索方面的有效性。此外，对我们的架构进行了消融研究，并评估了非监督和监督微调。值得注意的是，在 HisFrag20 上，SAGHOG 的 mAP 达到了 57.2％，比现有技术水平高出 11.6％，展示了其在具有挑战性的数据上的鲁棒性；在小数据集 GRK-Papyri 上，我们实现了 58.0％的 Top-1 准确率，表现出竞争性。