2LSPE: 2D Learnable Sinusoidal Positional Encoding using Transformer for Scene Text Recognition

Raisi, Zobeir; Naiel, Mohamed A.; Younes, Georges; Wardell, Steven; Zelek, John

doi:10.1109/crv52889.2021.00024

Cited by 9 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the authors proposed an adaptive 2D positional encoding as well as a locality-aware feed-forward module in the transformer encoder. With a focus on the positional encoding of transformer, Raisi et al [31] applied a 2D learnable sinusoidal positional encoding which enables the CNNtransformer encoder to focus more on spatial dependencies.…”

Section: Introductionmentioning

confidence: 99%

Pure Transformer with Integrated Experts for Scene Text Recognition

Tan,

Kong,

Kim

2022

Preprint

View full text Add to dashboard Cite

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework. In recent times, the transformer architecture is being widely adopted in STR as it shows strong capability in capturing long-term dependency which appears to be prominent in scene text images. Many researchers utilized transformer as part of a hybrid CNN-transformer encoder, often followed by a transformer decoder. However, such methods only make use of the long-term dependency mid-way through the encoding process. Although the vision transformer (ViT) is able to capture such dependency at an early stage, its utilization remains largely unexploited in STR. This work proposes the use of a transformer-only model as a simple baseline which outperforms hybrid CNN-transformer models. Furthermore, two key areas for improvement were identified. Firstly, the first decoded character has the lowest prediction accuracy. Secondly, images of different original aspect ratios react differently to the patch resolutions while ViT only employ one fixed patch resolution. To explore these areas, Pure Transformer with Integrated Experts (PTIE) is proposed. PTIE is a transformer model that can process multiple patch resolutions and decode in both the original and reverse character orders. It is examined on 7 commonly used benchmarks and compared with over 20 state-of-the-art methods. The experimental results show that the proposed method outperforms them and obtains state-of-the-art results in most benchmarks.

show abstract

Section: Introductionmentioning

confidence: 99%