Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
-
Updated
Feb 15, 2023 - Python
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
A novel teacher‑free distillation method that replaces live teacher inference with compact precomputed random projection teacher fingerprints, enabling storage-efficient, high-performance knowledge transfer and enhanced student training.
A modular teacher-free self-distillation framework that enhances camera-only BEV 3D detectors through EMA-based spatial–temporal consistency and uncertainty-aware feedback without modifying inference-time architecture.
Add a description, image, and links to the teacher-free topic page so that developers can more easily learn about it.
To associate your repository with the teacher-free topic, visit your repo's landing page and select "manage topics."