Conference
Open access
2026
XViT-Net: An Explainable Self-Supervised Vision Transformer Framework for Image Recognition
After running thorough benchmark image recognition trials, XViT-Net proved to be more accurate, resilient, and data efficient than the fully supervised Vision Transformer baselines and to be a trustworthy, interpretable, and data-efficient foundation for future image recognition systems.
Thilagavathi P, Praveen Kumar, Prince Kumar et al.
· ITM Web of Conferences · 0 citations