AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets

Skin lesion segmentation (SLS) plays an important role in skin lesion analysis. Vision transformers (ViTs) are considered an auspicious solution for SLS, but they require more training data compared to convolutional neural networks (CNNs) due to their inherent parameter-heavy structure and lack of some inductive biases.

Data and Resources

Cite this as

Siyi Du, Nourhan Bayasi, Ghassan Hamarneh, Rafeef Garbi (2025). Dataset: AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets. https://doi.org/10.57702/k5ak5jq3

DOI retrieved: January 2, 2025

Additional Info

Field Value
Created January 2, 2025
Last update January 2, 2025
Defined In https://doi.org/10.48550/arXiv.2307.13897
Author Siyi Du
More Authors
Nourhan Bayasi
Ghassan Hamarneh
Rafeef Garbi
Homepage https://github.com/siyi-wind/AViT