Vision Transformer for Fast and Efficient Scene Text Recognition
share
Scene text recognition (STR) enables computers to read text in natural scenes such as object labels, road signs and instructions. STR helps machines perform informed decisions such as what object to pick, which direction to go, and what is the next step of action. In the body of work on STR, the focus has always been on recognition accuracy. There is little emphasis placed on speed and computational efficiency which are equally important especially for energy-constrained mobile machines. In this paper we propose ViTSTR, an STR with a simple single stage model architecture built on a compute and parameter efficient vision transformer (ViT). On a comparable strong baseline method such as TRBA with accuracy of 84.3 accuracy of 82.6 43.4 achieves 80.3 requiring only 10.9 augmentation, our base ViTSTR outperforms TRBA at 85.2 augmentation) at 2.3x the speed but requires 73.2 more FLOPS. In terms of trade-offs, nearly all ViTSTR configurations are at or near the frontiers to maximize accuracy, speed and computational efficiency all at the same time.
READ FULL TEXT