Learning Beyond Labels
Self-Supervised Handwritten Text Recognition

This paper addresses a key challenge in Handwritten Text Recognition (HTR): the dependence on large volumes of labeled data. To overcome this, we propose a self-supervised learning (SSL) framework, LoGo-HTR, that minimizes labeling requirements while achieving strong recognition performance. We introduce a large-scale dataset, SSL-HWD, consisting of 10 million word-level handwritten images from diverse scanned documents, partitioned into a small labeled subset and a much larger unlabeled subset.

The LoGo-HTR framework combines a local contrastive loss for spatial consistency and a global decorrelation loss to enhance feature diversity. This dual objective enables robust, invariant, and spatially discriminative feature learning. Extensive experiments on standard HTR benchmarks, including multilingual and historical data, demonstrate that our method consistently outperforms state-of-the-art approaches, even when fine-tuned using only 20% of the available labeled training data.