Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors

arXiv:2312.05286v2 Announce Type: replace
Abstract: Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-scale labeled synthetic data (LSD) for pre-training text detectors. However, a synth-to-real domain gap emerges, further limiting the performance of text detectors. Differently, in this work, we propose FreeReal, a real-domain-aligned pre-training paradigm that enables the complementary strengths of both LSD and unlabeled real data (URD). Specifically, to …

abstract arxiv cs.cv data detection detection methods domain exploit gap however images pre-training real data scale synthetic synthetic data text training type