Semantic Segmentation using Vision Transformers: A Survey

This survey reviews and compares the performances of Vision Transformer (ViT) architectures designed for semantic segmentation using benchmarking datasets to yield knowledge regarding the implementations carried out in semantic segmentation and to discover more efficient methodologies using ViTs. We cover applications including land coverage analysis, autonomous driving, and medical image analysis, with a focus on how Vision Transformers can be adapted for dense prediction tasks in computer vision.

Download paper here

Recommended citation:

H. Thisanke, C. Deshan, K. Chamith, S. Seneviratne, R. Vidanaarachchi and D. Herath, “Semantic Segmentation using Vision Transformers: A Survey,” Engineering Applications of Artificial Intelligence, vol. 126, pp. 106669, 2023, doi: 10.1016/j.engappai.2023.106669.

BibTeX

@article{thisanke2023semantic,
  title={Semantic segmentation using vision transformers: A survey},
  author={Thisanke, Hans and Deshan, Chamli and Chamith, Kavindu and Seneviratne, Sachith and Vidanaarachchi, Rajith and Herath, Damayanthi},
  journal={Engineering Applications of Artificial Intelligence},
  volume={126},
  pages={106669},
  year={2023},
  publisher={Pergamon}
}