Transformer-Driven Explainable Deep Learning with Quantitative Attribution Validation for Liver Tumor Detection

High effect sizes (Cohen’s d) in all comparisons indicate that the gains in the new model’s performance are both statistically and practically significant.

also in 1,558 other papers

The proposed model’s effect sizes are also highly significant compared with state-of-the-art architectures such as ViT and Swin Transformer, demonstrating its commendable performance across a wide range of modeling paradigms.

also in 132,142 other papers