OAKD: Objective-Oriented Adaptive Knowledge Distillation via Curriculum-Guided Dynamic Weighting
- 26 June 2025
- book chapter
- Published by Springer Nature
- p. 258-273
Abstract
No abstract availableKeywords
This publication has 29 references indexed in Scilit:
- Knowledge distillation via instance-level sequence learningKnowledge-Based Systems, 2021
- Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification2020
- Learning sequence-to-sequence affinity metric for near-online multi-object trackingKnowledge and Information Systems, 2020
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Squeeze-and-Excitation Networks2018
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
- A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning2017
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015