Decoupled Knowledge with Ensemble Learning for Online Distillation
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.
Code (1)
Tasks
Ensemble LearningKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Semi-Supervised Learning with Online Knowledge Distillation for Skin Lesion Classification
Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain.…
Skin Lesion ClassificationKnowledge DistillationEnsemble LearningMixed Sample Augmentation for Online Distillation
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 DistillationPILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation
Pre-trained language models have become a crucial part of ranking systems and achieved very impressive effects recently. To maintain high performance while keeping efficient computations, knowledge distillation is widely…
Knowledge DistillationPeer Collaborative Learning for Online Knowledge Distillation
Traditional knowledge distillation uses a two-stage training strategy to transfer knowledge from a high-capacity teacher model to a compact student model, which relies heavily on the pre-trained teacher. Recent online kn…
Knowledge DistillationKnowledge Distillation by On-the-Fly Native Ensemble
Knowledge distillation is effective to train small and generalisable network models for meeting the low-memory and fast running requirements. Existing offline distillation methods rely on a strong pre-trained teacher, wh…
Computational Efficiencyimage-classificationImage ClassificationKnowledge Distillation