Tag: knowledge distillation

A knowledge-distilled MobileNetV2 model classified healthy, early and diseased wheat stripe mosaic virus stages in South African field images, reaching ...

A new incremental few-shot fault diagnosis framework uses a diffusion model to generate synthetic samples for rare new fault classes, ...

Researchers have built a framework that turns AI explanation maps into a single score capable of predicting when a breast ...

A new explainable AI pipeline converts breast histology classifiers' evidence into auditable, region-level attribution maps and fully reproducible SOAP-style clinical ...

A new deep learning system distills a high-accuracy pose estimation model into a lightweight edge-deployable AI coach that corrects athletes' ...

A Chinese team adapted a real-time detection transformer with focused distillation, stride-4 supervision, and fine-resolution decoder memory to find sparsely ...

A new review charts how distributed AI, cross-domain knowledge transfer, and foundation models are transforming resource management across the edge-cloud ...

Researchers developed Found-RL, an open-source platform that lets vision-language models mentor lightweight reinforcement learning agents asynchronously, producing compact autonomous driving ...

A new knowledge distillation framework compresses three large neural networks into a 6.97 MB model that classifies rice diseases, localizes ...

Researchers built a slimmed-down YOLO-based vision model that sorts dragon fruit into raw and ripe classes with over 98% accuracy ...