2 papers
cs.CV2025
Model compression using knowledge distillation with integrated gradients
David E. Hernandez, Jose Chang, Torbjörn E. M. Nordling
Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradi…
cs.LG2025
Knowledge Distillation: Enhancing Neural Network Compression with Integrated Gradients
David E. Hernandez, Jose Ramon Chang, Torbjörn E. M. Nordling
Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper propose…