This repository contains the original PyTorch implementation of the paper "Rethinking encoder-decoder architecture using vision transformer for colorectal polyp and surgical instruments segmentation ", which was published in the journal "Engineering Applications of Artificial Intelligence - Elsevier" with an impact factor of 7.5.
- GPU: NVIDIA GeForce RTX 2060 SUPER
- Python 3.9.7
- PyTorch: 2.0.0
- OpenCV: 4.6.0
- Numpy: 1.22.3
- Matplotlib: 3.5.1
Please cite the following paper if you use the MET-Net architecture in your project:
Iqbal, A., Ahmed, Z., Usman, M., & Malik, I. (2024). Rethinking encoder-decoder architecture using vision transformer for colorectal polyp and surgical instruments segmentation
. Engineering Applications of Artificial Intelligence, Volume 136, Part B, October 2024, 108962. DOI: https://doi.org/10.1016/j.engappai.2024.108962