A teacher-student knowledge distillation framework combining Swin Transformer and Vision Transformer reaches 99.78% and 99.28% accuracy with AUC 1.0 on two GI endoscopy datasets and uses Grad-CAM for interpretability.
EndoNet: A multiscale attention-based network for detecting gastrointestinal abnormalities
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Graph-Augmented knowledge Distillation based Dual-Stream Vision Transformer with Region-Aware Attention for Gastrointestinal Disease Classification with Explainable AI
A teacher-student knowledge distillation framework combining Swin Transformer and Vision Transformer reaches 99.78% and 99.28% accuracy with AUC 1.0 on two GI endoscopy datasets and uses Grad-CAM for interpretability.