Papers › 1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection

1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection

12 Jul 2021arXiv:2107.05534archive 2025-07-28

Yuxiang Zhong, Xianbiao Qi, Shanjun Li, Dengyi Gu, Yihao Chen, Peiyang Ning, Rong Xiao

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.

PaperPDFCode

Code

Yuxiang1995/ICDAR2021_MFD mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDeformable ConvolutionFocal LossGeneralized Focal LossSyncBN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections