For Table Recognition model, we utilize PP-LCNet, CSP-PAN and SLAHead to optimize the backbone module, feature fusion module and decoding module, respectively, which improved the table structure accuracy by 6\% with comparable inference speed.
Ranked #3 on Table Recognition on PubTabNet
For text recognizer, the base model is replaced from CRNN to SVTR, and we introduce lightweight text recognition network SVTR LCNet, guided training of CTC by attention, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML, and UIM to accelerate the model and improve the effect.
In recent years, image recognition applications have developed rapidly.
We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks.
Optical Character Recognition (OCR) systems have been widely used in various of application scenarios.
Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance.
Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications.
Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17. 9M images are used).
We present an object detection framework based on PaddlePaddle.
In this paper we establish the spectrum of the magnetic Laplacian, as a set of real numbers with multiplicities, on the Sierpinski gasket graph ($SG$) where the magnetic fluxes equal $\alpha$ through the upright triangles, and $\beta$ through the downright triangles.
Mathematical Physics Mesoscale and Nanoscale Physics Combinatorics Mathematical Physics Probability Spectral Theory 05C50, 11C20, 32M25, 37F50, 47A10, 58J50, 82D40