paper-with-me

Papers

Feature-map-level Online Adversarial Knowledge Distillation

2020-02-05 · ICML 2020 1 · Inseop Chung, SeongUk Park, Jangho Kim, Nojun Kwak

Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. Thus in this paper, we propose an online knowledge distillation method that transfers not only the knowledge of the class probabilities but also that of the feature map using the adversarial training framework. We train multiple networks simultaneously by employing discriminators to distinguish the feature map distributions of different networks. Each network has its corresponding discriminator which discriminates the feature map from its own as fake while classifying that of the other network as real. By training a network to fool the corresponding discriminator, it can learn the other network's feature map distribution. We show that our method performs better than the conventional direct alignment method such as L1 and is more suitable for online distillation. Also, we propose a novel cyclic learning scheme for training more than two networks together. We have applied our method to various network architectures on the classification task and discovered a significant improvement of performance especially in the case of training a pair of a small network and a large one.

📄 PDF Abstract BibTeX arXiv:2002.01775

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

AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation

2020-08-01 · ECCV 2020 8 · Xiaobing Zhang, Shijian Lu, Haigang Gong, Zhipeng Luo 외

Online knowledge distillation has attracted increasing interest recently, which jointly learns teacher and student models or an ensemble of student models simultaneously and collaboratively. On the other hand, existing w…

Knowledge DistillationTransfer Learning

Online Adversarial Knowledge Distillation for Graph Neural Networks

2021-12-28 · Can Wang, Zhe Wang, Defang Chen, Sheng Zhou 외

Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both teacher and student models are trained o…

Knowledge Distillation

MetaMixer: A Regularization Strategy for Online Knowledge Distillation

2023-03-14 · Maorong Wang, Ling Xiao, Toshihiko Yamasaki

Online knowledge distillation (KD) has received increasing attention in recent years. However, while most existing online KD methods focus on developing complicated model structures and training strategies to improve the…

Knowledge Distillation

Feature Adversarial Distillation for Point Cloud Classification

2023-06-25 · YuXing Lee, Wei Wu

Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adv…

ClassificationFADKnowledge DistillationModel Compression+2

FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detection

2023-03-10 · Yingguang Yang, Renyu Yang, Hao Peng, Yangyang Li 외

Social bot detection is of paramount importance to the resilience and security of online social platforms. The state-of-the-art detection models are siloed and have largely overlooked a variety of data characteristics fr…

Contrastive LearningKnowledge Distillation