1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 12 Jul 2021.
Builds on
21 of 27 references.
References · 21
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
- 2015Fast R-CNNcited by 2,930
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
- 2017Deformable Convolutional Networkscited by 1,481
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
- 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
- 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
9 more
- 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
- 2020ResNeSt: Split-Attention Networkscited by 445
- 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
- 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
- 2018Context Encoding for Semantic Segmentationcited by 289
- 2020Gradient Centralization: A New Optimization Technique for Deep Neural Networkscited by 82
- 2021PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTMLcited by 39
- 2019Weighted boxes fusion: Ensembling boxes from different object detection modelscited by 20
- 2021PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latexcited by 10
Built on by
Citing papers per year: 2025: 1.
1 paper.