Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition

arXiv:2405.05841v1 Announce Type: new
Abstract: In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or sequence contrastive learning. However, they omit modeling the linguistic information in text images, which is crucial for recognizing text. To simultaneously capture local character features and linguistic information in visual space, we propose Symmetric Superimposition Modeling (SSM). The objective of SSM is to …

abstract arxiv cs.cv data focus good however image images information modeling pre-training real data recognition reduce representation solution studies text training type visual