mmocr/configs/textdet/dbnet
AllentDan 39f99ac720
[Doc] update the link of DBNet (#1672)
* update the link of DBNet_r50

* update the link of DBNet_r50-oclip
2023-01-12 11:06:53 +08:00
..
README.md [Doc] update the link of DBNet (#1672) 2023-01-12 11:06:53 +08:00
_base_dbnet_resnet18_fpnc.py [Config] Refactor base config (part 1) (#1314) 2022-08-23 22:43:07 +08:00
_base_dbnet_resnet50-dcnv2_fpnc.py [Config] Rename DB, DB++ and DRRG (#1296) 2022-08-22 12:49:24 +08:00
dbnet_resnet18_fpnc_100k_synthtext.py [Config] rename base dataset terms to {dataset-name}_task_train/test (#1541) 2022-11-17 10:15:33 +08:00
dbnet_resnet18_fpnc_1200e_icdar2015.py [Config] rename base dataset terms to {dataset-name}_task_train/test (#1541) 2022-11-17 10:15:33 +08:00
dbnet_resnet18_fpnc_1200e_totaltext.py [Configs] Totaltext cfgs for DB and FCE (#1633) 2022-12-28 11:51:38 +08:00
dbnet_resnet50-dcnv2_fpnc_100k_synthtext.py [Config] rename base dataset terms to {dataset-name}_task_train/test (#1541) 2022-11-17 10:15:33 +08:00
dbnet_resnet50-dcnv2_fpnc_1200e_icdar2015.py [Config] rename base dataset terms to {dataset-name}_task_train/test (#1541) 2022-11-17 10:15:33 +08:00
dbnet_resnet50-oclip_1200e_icdar2015.py [Config] Add oCLIP configs (#1509) 2022-11-03 17:57:13 +08:00
dbnet_resnet50_1200e_icdar2015.py [Config] Add oCLIP configs (#1509) 2022-11-03 17:57:13 +08:00
metafile.yml [Metafile] Add Aliases to models (#1611) 2022-12-29 17:44:32 +08:00

README.md

DBNet

Real-time Scene Text Detection with Differentiable Binarization

Abstract

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text. In this paper, we propose a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network. Optimized along with a DB module, a segmentation network can adaptively set the thresholds for binarization, which not only simplifies the post-processing but also enhances the performance of text detection. Based on a simple segmentation network, we validate the performance improvements of DB on five benchmark datasets, which consistently achieves state-of-the-art results, in terms of both detection accuracy and speed. In particular, with a light-weight backbone, the performance improvements by DB are significant so that we can look for an ideal tradeoff between detection accuracy and efficiency. Specifically, with a backbone of ResNet-18, our detector achieves an F-measure of 82.8, running at 62 FPS, on the MSRA-TD500 dataset.

Results and models

ICDAR2015

Method Backbone Pretrained Model Training set Test set #epochs Test size Precision Recall Hmean Download
DBNet_r18 ResNet18 - ICDAR2015 Train ICDAR2015 Test 1200 736 0.8853 0.7583 0.8169 model | log
DBNet_r50 ResNet50 - ICDAR2015 Train ICDAR2015 Test 1200 1024 0.8744 0.8276 0.8504 model | log
DBNet_r50dcn ResNet50-DCN Synthtext ICDAR2015 Train ICDAR2015 Test 1200 1024 0.8784 0.8315 0.8543 model | log
DBNet_r50-oclip ResNet50-oCLIP - ICDAR2015 Train ICDAR2015 Test 1200 1024 0.9052 0.8272 0.8644 model | log

Total Text

Method Backbone Pretrained Model Training set Test set #epochs Test size Precision Recall Hmean Download
DBNet_r18 ResNet18 - Totaltext Train Totaltext Test 1200 736 0.8640 0.7770 0.8182 model | log

Citation

@article{Liao_Wan_Yao_Chen_Bai_2020,
    title={Real-Time Scene Text Detection with Differentiable Binarization},
    journal={Proceedings of the AAAI Conference on Artificial Intelligence},
    author={Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang},
    year={2020},
    pages={11474-11481}}