Papers › Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition

Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition

23 Jul 2022arXiv:2207.11518archive 2025-07-28

Chuanguang Yang, Zhulin An, Helong Zhou, Fuzhen Zhuang, Yongjun Xu, Qian Zhan

The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing online KD methods achieve desirable performance, they often focus on class probabilities as the core knowledge type, ignoring the valuable feature representational information. We present a Mutual Contrastive Learning (MCL) framework for online KD. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks in an online manner. Our MCL can aggregate cross-network embedding information and maximize the lower bound to the mutual information between two networks. This enables each network to learn extra contrastive knowledge from others, leading to better feature representations, thus improving the performance of visual recognition tasks. Beyond the final layer, we extend MCL to intermediate layers and perform an adaptive layer-matching mechanism trained by meta-optimization. Experiments on image classification and transfer learning to visual recognition tasks show that layer-wise MCL can lead to consistent performance gains against state-of-the-art online KD approaches. The superiority demonstrates that layer-wise MCL can guide the network to generate better feature representations. Our code is publicly avaliable at https://github.com/winycg/L-MCL.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

winycg/l-mcl officialmentioned in papermentioned on GitHubpytorch report
winycg/mcl officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningImage ClassificationKnowledge DistillationNetwork EmbeddingRepresentation LearningTransfer Learningimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningKnowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections