SOURCE-LINKED INTELLIGENCE

Transferring Visual Explanations: How Cross-Architecture Knowledge Distillation Affects Model Interpretability

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical in safety-critical domains such as autonomous driving and medicine. This study investigates whether Knowledge Distillation transfers the spatial feature attribution of a large teacher network to a compact student. To assess the influence of the KD scheme on interpretability, we distill a ResNet-152 teacher into a ResNet-34 student on ImageNet-1K across five configurations by systematically varying the distillation temperature and soft-label los

Read original source ↗ Open in workspace

recordType

paper

region

Global