Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing

I Hong, Y Jo, H Lee, S Ahn, S Park - arxiv preprint arxiv:2412.19125, 2024 - arxiv.org
We introduce AKT (Advanced Knowledge Transfer), a novel method to enhance the training
ability of low-bit quantized (Q) models in the field of zero-shot quantization (ZSQ). Existing …

Q_YOLOv5m: A Quantization-based Approach for Accelerating Object Detection on Embedded Platforms

N Alshammry, T Saidani, NS Albalawi… - … , Technology & Applied …, 2025 - etasr.com
The deployment of deep learning models on resource-constrained embedded platforms
presents significant challenges due to limited computational power, memory, and energy …

Towards Eight-Bit Quantization for 3D U-Net Medical Image Segmentation via ROI-Based Calibration and Background-Aware Shift

S Kim, M Cha, C Yi, XT Nguyen - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
3D U-Net medical image segmentation is essential for precise diagnosis and treatment
planning but comes with massive bandwidth requirements and considerable computational …

[PDF][PDF] Quantization Strategies in Federated Learning: Comparative Assessment of Methods and Challenges

P Dubey - Authorea Preprints, 2024 - techrxiv.org
FL presents an encouraging system for collectively training machine learning models on
decentralized devices while maintaining data privacy. However, the difficulties of restricted …