Dealing with unreliable annotations: noise-robust network for semantic segmentation through transformer-improved-encoder and convolution-decoder
Conventional deep learning methods have shown promising results in the medical domain when trained on accurate ground truth data. Pragmatically, due to constraints like lack of time or annotator inexperience, the ground truth data obtained from clinical environments may not always be impeccably accu...
| Autores principales: | , |
|---|---|
| Formato: | Journal article |
| Lenguaje: | English |
| Publicado: |
Asian Network for Scientific Information
2023
|