Papers › Wasserstein Contrastive Representation Distillation

Wasserstein Contrastive Representation Distillation

15 Dec 2020CVPR 2021 1arXiv:2012.08674archive 2025-07-28

Liqun Chen, Dong Wang, Zhe Gan, Jingjing Liu, Ricardo Henao, Lawrence Carin

The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former. Existing work, e.g., using Kullback-Leibler divergence for distillation, may fail to capture important structural knowledge in the teacher network and often lacks the ability for feature generalization, particularly in situations when teacher and student are built to address different classification tasks. We propose Wasserstein Contrastive Representation Distillation (WCoRD), which leverages both primal and dual forms of Wasserstein distance for KD. The dual form is used for global knowledge transfer, yielding a contrastive learning objective that maximizes the lower bound of mutual information between the teacher and the student networks. The primal form is used for local contrastive knowledge transfer within a mini-batch, effectively matching the distributions of features between the teacher and the student networks. Experiments demonstrate that the proposed WCoRD method outperforms state-of-the-art approaches on privileged information distillation, model compression and cross-modal transfer.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Contrastive LearningKnowledge DistillationModel CompressionTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Distillation CIFAR-100 resnet8x4 (T: resnet32x4 S: resnet8x4) Top-1 Accuracy (%) 76.15 #12 of 27 Archive leaderboard report
Knowledge Distillation CIFAR-100 vgg8 (T:vgg13 S:vgg8) Top-1 Accuracy (%) 74.72 #18 of 27 Archive leaderboard report
Knowledge Distillation CIFAR-100 resnet110 (T:resnet110 S:resnet20) Top-1 Accuracy (%) 71.88 #24 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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