TESTR: Text Spotting Transformers

This repository is the official implementations for the following paper:

Text Spotting Transformers

Xiang Zhang, Yongwen Su, Subarna Tripathi, and Zhuowen Tu, CVPR 2022

Getting Started

We use the following environment in our experiments. It's recommended to install the dependencies via Anaconda

CUDA 11.3
Python 3.8
PyTorch 1.10.1
Official Pre-Built Detectron2

Installation

Please refer to the Installation section of AdelaiDet: README.md.

If you have not installed Detectron2, following the official guide: INSTALL.md.

After that, build this repository with

python setup.py build develop

Preparing Datasets

Please download TotalText, CTW1500, MLT, and CurvedSynText150k according to the guide provided by AdelaiDet: README.md.

ICDAR2015 dataset can be download via link.

Extract all the datasets and make sure you organize them as follows

- datasets
  | - CTW1500
  |   | - annotations
  |   | - ctwtest_text_image
  |   | - ctwtrain_text_image
  | - totaltext (or icdar2015)
  |   | - test_images
  |   | - train_images
  |   | - test.json
  |   | - train.json
  | - mlt2017 (or syntext1, syntext2)
      | - annotations
      | - images

After that, download polygonal annotations, along with evaluation files and extract them under datasets folder.

Visualization Demo

You can try to visualize the predictions of the network using the following command:

python demo/demo.py --config-file <PATH_TO_CONFIG_FILE> --input <FOLDER_TO_INTPUT_IMAGES> --output <OUTPUT_FOLDER> --opts MODEL.WEIGHTS <PATH_TO_MODEL_FILE> MODEL.TRANSFORMER.INFERENCE_TH_TEST 0.3

You may want to adjust INFERENCE_TH_TEST to filter out predictions with lower scores.

Training

You can train from scratch or finetune the model by putting pretrained weights in weights folder.

Example commands:

python tools/train_net.py --config-file <PATH_TO_CONFIG_FILE> --num-gpus 8

All configuration files can be found in configs/TESTR, excluding those files named Base-xxxx.yaml.

TESTR_R_50.yaml is the config for TESTR-Bezier, while TESTR_R_50_Polygon.yaml is for TESTR-Polygon.

Evaluation

python tools/train_net.py --config-file <PATH_TO_CONFIG_FILE> --eval-only MODEL.WEIGHTS <PATH_TO_MODEL_FILE>

Pretrained Models

Dataset	Annotation Type	Lexicon	Det-P	Det-R	Det-F	E2E-P	E2E-R	E2E-F	Link
Pretrain	Bezier	None	88.87	76.47	82.20	63.58	56.92	60.06	OneDrive
Pretrain	Polygonal	None	88.18	77.51	82.50	66.19	61.14	63.57	OneDrive
TotalText	Bezier	None	92.83	83.65	88.00	74.26	69.05	71.56	OneDrive
	Bezier	Full	-	-	-	86.42	80.35	83.28	OneDrive
	Polygonal	None	93.36	81.35	86.94	76.85	69.98	73.25	OneDrive
	Polygonal	Full	-	-	-	88.00	80.13	83.88	OneDrive
CTW1500	Bezier	None	89.71	83.07	86.27	55.44	51.34	53.31	OneDrive
	Bezier	Full	-	-	-	83.05	76.90	79.85	OneDrive
	Polygonal	None	92.04	82.63	87.08	59.14	53.09	55.95	OneDrive
	Polygonal	Full	-	-	-	86.16	77.34	81.51	OneDrive
ICDAR15	Polygonal	None	90.31	89.70	90.00	65.49	65.05	65.27	OneDrive
		Strong	-	-	-	87.11	83.29	85.16
		Weak	-	-	-	80.36	78.38	79.36
		Generic	-	-	-	73.82	73.33	73.57

The Lite models only use the image feature from the last stage of ResNet.

Method	Annotation Type	Lexicon	Det-P	Det-R	Det-F	E2E-P	E2E-R	E2E-F	Link
Pretrain (Lite)	Polygonal	None	90.28	72.58	80.47	59.49	50.22	54.46	OneDrive
TotalText (Lite)	Polygonal	None	92.16	79.09	85.12	66.42	59.06	62.52	OneDrive

Citation

@InProceedings{Zhang_2022_CVPR,
    author    = {Zhang, Xiang and Su, Yongwen and Tripathi, Subarna and Tu, Zhuowen},
    title     = {Text Spotting Transformers},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {9519-9528}
}

License

This repository is released under the Apache License 2.0. License can be found in LICENSE file.

Acknowledgement

Thanks to AdelaiDet for a standardized training and inference framework, and Deformable-DETR for the implementation of multi-scale deformable cross-attention.

huycq1712/TESTR