File size: 300 Bytes
5fa1a76
 
 
1
2
3
The effectiveness of initializing image-to-text-sequence models with pretrained checkpoints has been shown in (for
example) TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models by Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang,
Zhoujun Li, Furu Wei.