# 1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit

arXiv: https://arxiv.org/abs/2104.03544 · HTML: https://mlsanity.com/paper/2104.03544/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [IoU-aware Single-stage Object Detector for Accurate Localization](https://mlsanity.com/paper/1912.05992/) (2019)
- [Weighted boxes fusion: Ensembling boxes from different object detection models](https://mlsanity.com/paper/1910.13302/) (2019)

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

- [ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment](https://mlsanity.com/paper/2107.05279/) (2021)

## Abstract (arXiv)

This paper presents our proposed methods to ICDAR 2021 Robust Reading Challenge - Integrated Circuit Text Spotting and Aesthetic Assessment (ICDAR RRC-ICTEXT 2021). For the text spotting task, we detect the characters on integrated circuit and classify them based on yolov5 detection model. We balance the lowercase and non-lowercase by using SynthText, generated data and data sampler. We adopt semi-supervised algorithm and distillation to furtherly improve the model's accuracy. For the aesthetic assessment task, we add a classification branch of 3 classes to differentiate the aesthetic classes of each character. Finally, we make model deployment to accelerate inference speed and reduce memory consumption based on NVIDIA Tensorrt. Our methods achieve 59.1 mAP on task 3.1 with 31 FPS and 306M memory (rank 1), 78.7% F2 score on task 3.2 with 30 FPS and 306M memory (rank 1).