# Decoupled Knowledge with Ensemble Learning for Online Distillation

arXiv: https://arxiv.org/abs/2312.11218 · HTML: https://mlsanity.com/paper/2312.11218/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Online Knowledge Distillation with Diverse Peers](https://mlsanity.com/paper/1912.00350/) (2019)
- [A Survey of Modern Deep Learning based Object Detection Models](https://mlsanity.com/paper/2104.11892/) (2021)
- [Collaborative Learning for Deep Neural Networks](https://mlsanity.com/paper/1805.11761/) (2018)
- [Peer Collaborative Learning for Online Knowledge Distillation](https://mlsanity.com/paper/2006.04147/) (2020)
- [Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum](https://mlsanity.com/paper/2006.15815/) (2020)
- [Online Knowledge Distillation via Multi-branch Diversity Enhancement](https://mlsanity.com/paper/2010.00795/) (2020)
- [Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution](https://mlsanity.com/paper/2109.03075/) (2021)

## Abstract (arXiv)

Offline distillation is a two-stage pipeline that requires expensive resources to train a teacher network and then distill the knowledge to a student for deployment. Online knowledge distillation, on the other hand, is a one-stage strategy that alleviates the requirement with mutual learning and collaborative learning. Recent peer collaborative learning (PCL) integrates online ensemble, collaboration of base networks and temporal mean teacher to construct effective knowledge. However, the model collapses occasionally in PCL due to high homogenization between the student and the teacher. In this paper, the cause of the high homogenization is analyzed and the solution is presented. A decoupled knowledge for online knowledge distillation is generated by an independent teacher, separate from the student. Such design can increase the diversity between the networks and reduce the possibility of model collapse. To obtain early decoupled knowledge, an initialization scheme for the teacher is devised, and a 2D geometry-based analysis experiment is conducted under ideal conditions to showcase the effectiveness of this scheme. Moreover, to improve the teacher's supervisory resilience, a decaying ensemble scheme is devised. It assembles the knowledge of the teacher to which a dynamic weight which is large at the start of the training and gradually decreases with the training process is assigned. The assembled knowledge serves as a strong teacher during the early training and the decreased-weight-assembled knowledge can eliminate the distribution deviation under the potentially overfitted teacher's supervision. A Monte Carlo-based simulation is conducted to evaluate the convergence. Extensive experiments on CIFAR-10, CIFAR-100 and TinyImageNet show the superiority of our method. Ablation studies and further analysis demonstrate the effectiveness.