Tiny and Efficient Edge Detector (TEED) is a light convolutional neural network with only $58K$ parameters, less than $0.2$% of the state-of-the-art models. Training on the BIPED dataset takes less than 30 minutes, with each epoch requiring less than 5 minutes. Our proposed model is easy to train and it quickly converges within very first few epochs, while the predicted edge-maps are crisp and of high quality, see image above. This paper has been accepted by ICCV 2023-Workshop RCV.

... In construction

git clone https://github.com/xavysp/TEED.git
cd TEED

Then,

Copy and paste your images into data/ folder, and:

python main.py --choose_test_data=-1

Set the following lines in main.py:

25: is_testing =False
# training with BIPED
223: TRAIN_DATA = DATASET_NAMES[0] 

then run

python main.py

Check the configurations of the datasets in dataset.py

Here the link to access the UDED dataset for edge detection

If you like TEED, why not starring the project on GitHub!

Please cite our Dataset if you find helpful in your academic/scientific publication,

@InProceedings{Soria_2023teed,
    author    = {Soria, Xavier and Li, Yachuan and Rouhani, Mohammad and Sappa, Angel D.},
    title     = {Tiny and Efficient Model for the Edge Detection Generalization},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
    month     = {October},
    year      = {2023},
    pages     = {1364-1373}
}