We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different writer distribution. We have compared the performance of multiple generative, contrastive SSL approaches against handcrafted feature extractors and supervised learning on CEDAR AND dataset. We show that ResNet based Variational Auto-Encoder (VAE) outperforms other generative approaches achieving 76.3% accuracy, while ResNet-18 fine-tuned using Variance-Invariance-Covariance Regularization (VICReg) outperforms other contrastive approaches achieving 78% accuracy. Using a pre-trained VAE and VICReg for the downstream task of writer verification we observed a relative improvement in accuracy of 6.7% and 9% over ResNet-18 supervised baseline with 10% writer labels.
翻译:本文提出SSL-HV:一种应用于手写笔迹验证任务的自监督学习方法。该任务旨在判定给定的一对手写图像是否源自同一书写者分布。我们在CEDAR AND数据集上,将多种生成式与对比式自监督学习方法与手工特征提取器及监督学习方法进行了性能比较。实验表明,基于ResNet的变分自编码器(VAE)在生成式方法中表现最优,达到76.3%的准确率;而采用方差-不变性-协方差正则化(VICReg)微调的ResNet-18在对比式方法中表现最佳,获得78%的准确率。通过将预训练的VAE与VICReg模型应用于书写者验证的下游任务,我们观察到相较于仅使用10%书写者标签的ResNet-18监督基线模型,准确率分别实现了6.7%和9%的相对提升。