A Hybrid Vision Transformer Approach for Mathematical Expression Recognition

TL;DR

This paper introduces a Hybrid Vision Transformer model with 2D positional encoding and a coverage attention decoder for improved mathematical expression recognition, achieving state-of-the-art results on the IM2LATEX-100K dataset.

Contribution

The paper presents a novel Hybrid Vision Transformer architecture with 2D positional encoding and a coverage attention decoder for better recognition of complex mathematical expressions.

Findings

Achieved a BLEU score of 89.94 on IM2LATEX-100K dataset.

Outperformed existing state-of-the-art methods.

Demonstrated the effectiveness of the HVT approach.

Abstract

One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much more complicated problem because of its two-dimensional structure and different symbol size. In this paper, we propose using a Hybrid Vision Transformer (HVT) with 2D positional encoding as the encoder to extract the complex relationship between symbols from the image. A coverage attention decoder is used to better track attention's history to handle the under-parsing and over-parsing problems. We also showed the benefit of using the [CLS] token of ViT as the initial embedding of the decoder. Experiments performed on the IM2LATEX-100K dataset have shown the effectiveness of our method by achieving a BLEU score of 89.94 and outperforming current state-of-the-art methods.