Why logit distillation works: A novel knowledge distillation technique by deriving target augmentation and logits distortion
- 13 January 2025
- journal article
- Published by Elsevier in Information Processing & Management
- Vol. 62 (3)
Abstract
No abstract availableThis publication has 59 references indexed in Scilit:
- KDCTime: Knowledge distillation with calibration on InceptionTime for time-series classificationInformation Sciences, 2022
- Knowledge distillation guided by multiple homogeneous teachersInformation Sciences, 2022
- A multi-autoencoder fusion network guided by perceptual distillationInformation Sciences, 2022
- A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillationInformation Sciences, 2022
- Online knowledge distillation with elastic peerInformation Sciences, 2022
- Item-side ranking regularized distillation for recommender systemInformation Sciences, 2021
- Top-aware recommender distillation with deep reinforcement learningInformation Sciences, 2021
- Distilling from professors: Enhancing the knowledge distillation of teachersInformation Sciences, 2021
- Classifier-adaptation knowledge distillation framework for relation extraction and event detection with imbalanced dataInformation Sciences, 2021
- Block change learning for knowledge distillationInformation Sciences, 2020