# SemiHMER: Semi-supervised Handwritten Mathematical Expression Recognition using pseudo-labels

arXiv: https://arxiv.org/abs/2502.07172 · HTML: https://mlsanity.com/paper/2502.07172/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 22 of 22)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Syntax-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2203.01601/) (2022)
- [Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection](https://mlsanity.com/paper/2209.01589/) (2022)
- [Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/1801.03530/) (2018)
- [When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2207.11463/) (2022)
- [Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention](https://mlsanity.com/paper/2007.10092/) (2020)
- [Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning](https://mlsanity.com/paper/2112.03603/) (2021)
- [PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer](https://mlsanity.com/paper/2407.07764/) (2024)
- [A Survey on Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.09899/) (2023)
- [Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection](https://mlsanity.com/paper/2303.14960/) (2023)
- [TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2408.08578/) (2024)
- [A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/1712.03991/) (2017)
- [Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2308.10493/) (2023)
- [GLA-DA: Global-Local Alignment Domain Adaptation for Multivariate Time Series](https://mlsanity.com/paper/2410.06671/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards Scalable Training for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2508.09220/) (2025)

## Abstract (arXiv)

In this paper, we study semi-supervised Handwritten Mathematical Expression Recognition (HMER) via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization framework, termed SemiHMER, which introduces dual-branch semi-supervised learning. Specifically, we enforce consistency between the two networks for the same input image. The pseudo-label, generated by one perturbed recognition network, is utilized to supervise the other network using the standard cross-entropy loss. The SemiHMER consistency encourages high similarity between the predictions of the two perturbed networks for the same input image and expands the training data by leveraging unlabeled data with pseudo-labels. We further introduce a weak-to-strong strategy by applying different levels of augmentation to each branch, effectively expanding the training data and enhancing the quality of network training. Additionally, we propose a novel module, the Global Dynamic Counting Module (GDCM), to enhance the performance of the HMER decoder by alleviating recognition inaccuracies in long-distance formula recognition and reducing the occurrence of repeated characters. The experimental results demonstrate that our work achieves significant performance improvements, with an average accuracy increase of 5.47% on CROHME14, 4.87% on CROHME16, and 5.25% on CROHME19, compared to our baselines.