1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
This work solves the problem of detecting mathematical formulas in documents for researchers and practitioners in document analysis, but it is incremental as it builds on existing methods.
The authors tackled the mathematical formula detection task by addressing challenges like scale variation and character diversity, achieving first place in the ICDAR 2021 competition.
In this technical report, we present our 1st place solution for the ICDAR 2021 competition on mathematical formula detection (MFD). The MFD task has three key challenges including a large scale span, large variation of the ratio between height and width, and rich character set and mathematical expressions. Considering these challenges, we used Generalized Focal Loss (GFL), an anchor-free method, instead of the anchor-based method, and prove the Adaptive Training Sampling Strategy (ATSS) and proper Feature Pyramid Network (FPN) can well solve the important issue of scale variation. Meanwhile, we also found some tricks, e.g., Deformable Convolution Network (DCN), SyncBN, and Weighted Box Fusion (WBF), were effective in MFD task. Our proposed method ranked 1st in the final 15 teams.