paper-with-me

Papers

FEED: Feature-level Ensemble for Knowledge Distillation

2019-09-24 · SeongUk Park, Nojun Kwak

Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can use either a teacher with high capacity or {an} ensemble of multiple teachers. However, the latter is not convenient when one wants to use feature-map-based distillation methods. For a solution, this paper proposes a versatile and powerful training algorithm named FEature-level Ensemble for knowledge Distillation (FEED), which aims to transfer the ensemble knowledge using multiple teacher networks. We introduce a couple of training algorithms that transfer ensemble knowledge to the student at the feature map level. Among the feature-map-based distillation methods, using several non-linear transformations in parallel for transferring the knowledge of the multiple teacher{s} helps the student find more generalized solutions. We name this method as parallel FEED, andexperimental results on CIFAR-100 and ImageNet show that our method has clear performance enhancements, without introducing any additional parameters or computations at test time. We also show the experimental results of sequentially feeding teacher's information to the student, hence the name sequential FEED, and discuss the lessons obtained. Additionally, the empirical results on measuring the reconstruction errors at the feature map give hints for the enhancements.

📄 PDF Abstract BibTeX arXiv:1909.10754

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

FEED: Feature-level Ensemble Effect for knowledge Distillation

2019-05-01 · ICLR 2019 5 · SeongUk Park, Nojun Kwak

This paper proposes a versatile and powerful training algorithm named Feature-level Ensemble Effect for knowledge Distillation(FEED), which is inspired by the work of factor transfer. The factor transfer is one of the kn…

Knowledge DistillationTransfer Learning

Mixed Sample Augmentation for Online Distillation

2022-06-24 · Yiqing Shen, Liwu Xu, Yuzhe Yang, Yaqian Li 외

Mixed Sample Regularization (MSR), such as MixUp or CutMix, is a powerful data augmentation strategy to generalize convolutional neural networks. Previous empirical analysis has illustrated an orthogonal performance gain…

Data AugmentationKnowledge Distillation

Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning

2025-07-14 · Yichen Li

Model-Heterogeneous Federated Learning (Hetero-FL) has attracted growing attention for its ability to aggregate knowledge from heterogeneous models while keeping private data locally. To better aggregate knowledge from c…

Federated LearningKnowledge Distillation

Knowledge Distillation based Ensemble Learning for Neural Machine Translation

2021-01-01 · Chenze Shao, Meng Sun, Yang Feng, Zhongjun He 외

Model ensemble can effectively improve the accuracy of neural machine translation, which is accompanied by the cost of large computation and memory requirements. Additionally, model ensemble cannot combine the strengths …

Ensemble LearningKnowledge DistillationMachine TranslationTranslation

CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data

2022-03-13 · Ke Zhang, Jin Fan, Shaoli Huang, Yongliang Qiao 외

Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics …

Data AugmentationKnowledge Distillation