# Deep Ensemble Collaborative Learning by using Knowledge-transfer Graph for Fine-grained Object Classification

arXiv: https://arxiv.org/abs/2103.14845 · HTML: https://mlsanity.com/paper/2103.14845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 27 Mar 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Ensemble Distribution Distillation](https://mlsanity.com/paper/1905.00076/) (2019)
- [Hyperparameter Ensembles for Robustness and Uncertainty Quantification](https://mlsanity.com/paper/2006.13570/) (2020)
- [Attention Branch Network: Learning of Attention Mechanism for Visual Explanation](https://mlsanity.com/paper/1812.10025/) (2018)
- [Diversity with Cooperation: Ensemble Methods for Few-Shot Classification](https://mlsanity.com/paper/1903.11341/) (2019)
- [Collaborative Learning for Deep Neural Networks](https://mlsanity.com/paper/1805.11761/) (2018)
- [Learning Metrics from Teachers: Compact Networks for Image Embedding](https://mlsanity.com/paper/1904.03624/) (2019)
- [Knowledge Transfer Graph for Deep Collaborative Learning](https://mlsanity.com/paper/1909.04286/) (2019)

## Abstract (arXiv)

Mutual learning, in which multiple networks learn by sharing their knowledge, improves the performance of each network. However, the performance of ensembles of networks that have undergone mutual learning does not improve significantly from that of normal ensembles without mutual learning, even though the performance of each network has improved significantly. This may be due to the relationship between the knowledge in mutual learning and the individuality of the networks in the ensemble. In this study, we propose an ensemble method using knowledge transfer to improve the accuracy of ensembles by introducing a loss design that promotes diversity among networks in mutual learning. We use an attention map as knowledge, which represents the probability distribution and information in the middle layer of a network. There are many ways to combine networks and loss designs for knowledge transfer methods. Therefore, we use the automatic optimization of knowledge-transfer graphs to consider a variety of knowledge-transfer methods by graphically representing conventional mutual-learning and distillation methods and optimizing each element through hyperparameter search. The proposed method consists of a mechanism for constructing an ensemble in a knowledge-transfer graph, attention loss, and a loss design that promotes diversity among networks. We explore optimal ensemble learning by optimizing a knowledge-transfer graph to maximize ensemble accuracy. From exploration of graphs and evaluation experiments using the datasets of Stanford Dogs, Stanford Cars, and CUB-200-2011, we confirm that the proposed method is more accurate than a conventional ensemble method.