search

roatienza / deep-text-recognition-benchmark

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)
Apache License 2.0
293 stars 59 forks source link

Is there any performance comparison with clovaai/deep-text-recognition-benchmark #14

Open LLC opened 3 years ago

LLC commented 3 years ago

Hi, I trained two text recognition models (my own data) using following repos: [1] clovaai/deep-text-recognition-benchmark [2] roatienza/deep-text-recognition-benchmark

but [1] got better accuracy ([1] accuracy: 0.94, [2] accuracy: 0.85) Is there any performance comparison with [1] on open dataset? Is there any suggestion that I need to aware? Thanks a lot.

roatienza commented 3 years ago

There are various techniques that can be used to improve the performance of transformer based models. The simplest is training on a large dataset to overcome the lack of inductive bias in transformers. There are many large synthetic STR datasets that you can use to do this.