Papers › Contrastive Prototypical Network with Wasserstein Confidence Penalty

Contrastive Prototypical Network with Wasserstein Confidence Penalty

21 Oct 2022European Conference on Computer Vision 2022 10archive 2025-07-28

Haoqing Wang, Zhi-Hong Deng

Unsupervised few-shot learning aims to learn the inductive bias from unlabeled dataset for solving the novel few-shot tasks. The existing unsupervised few-shot learning models and the contrastive learning models follow a unified paradigm. Therefore, we conduct empirical study under this paradigm and find that pairwise contrast, meta losses and large batch size are the important design factors. This results in our CPN (Contrastive Prototypical Network) model, which combines the prototypical loss with pairwise contrast and outperforms the existing models from this paradigm with modestly large batch size. Furthermore, the one-hot prediction target in CPN could lead to learning the sample-specific information. To this end, we propose Wasserstein Confidence Penalty which can impose appropriate penalty on overconfident predictions based on the semantic relationships among pseudo classes. Our full model, CPNWCP (Contrastive Prototypical Network with Wasserstein Confidence Penalty), achieves state-of-the-art performance on miniImageNet and tieredImageNet under unsupervised setting. Our code is available at https://github.com/Haoqing-Wang/CPNWCP.

PaperPDFCode

Code

Haoqing-Wang/CPNWCP mentioned 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 LearningFew-Shot LearningInductive BiasUnsupervised Few-Shot Image ClassificationUnsupervised Few-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) CPNWCP Accuracy 53.56 #11 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) CPNWCP Accuracy 73.21 #9 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) CPNWCP Accuracy 45.00 #9 of 12 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) CPNWCP Accuracy 62.96 #9 of 12 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

CPNContrastive LearningConvolutionNon Maximum Suppression

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