Questions for reimplementing ABINet about abinet HOT 3 OPEN

I've sent an email to the authors and received their reply. To help researchers who want to conduct reimplementation, here are their responses:

1. The backbone used in this paper is ResNet45 which is exactly the same as those used in ASTER and DAN. "5 residual blocks" in the paper actually means "5 residual stages or layers".
2. Q is hard-coded and is sent to an fc layer to project it.
3. Augmentation strategy will be released along with the code and it can make good performance gain especially in irregular texts.
4. 4-5 days.

Besides, I've made an attempt to reimplement the vision part of this model, but achieved a much worse result. My average precision of the vision model is about 85+%, while the performance reported in the paper is 88+%.

If anyone has also tried to reimplement or has achieved higher performance, please leave a message here on how you make it if possible, that will be great help and big thanks in advance.

from abinet.

Use parallel attention for vision model, still cannot hit 88.8% mentioned in paper.😅

from abinet.

How about your accuracy now. Do you use Transformer as the sequence modeling layer, and use data augmentation?
We'll release our code next week or so.

from abinet.