Papers › Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
Xingping Dong, Jianbing Shen, Ling Shao
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it often suffers from label inconsistency or limited diversity, which leads to poor performance. In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space. We address this by minimizing the inter- to intra-class similarity ratio to provide clustering-friendly embedding features, and validate our approach through comprehensive experiments. Note that, despite only utilizing a simple clustering algorithm (k-means) in our embedding space to obtain the pseudo-labels, we achieve significant improvement. Moreover, we adopt a progressive evaluation mechanism to obtain more diverse samples in order to further alleviate the limited diversity problem. Finally, our approach is also model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in two tasks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Unsupervised Few-Shot Image Classification | Mini-Imagenet 5-way (1-shot) | PL-CFE | Accuracy | 49.13 | #13 of 28 | Archive leaderboard | report |
| Unsupervised Few-Shot Image Classification | Mini-Imagenet 5-way (5-shot) | PL-CFE | Accuracy | 62.91 | #17 of 28 | Archive leaderboard | report |
| Unsupervised Few-Shot Image Classification | Tiered ImageNet 5-way (1-shot) | PL-CFE | Accuracy | 49.51 | #7 of 12 | Archive leaderboard | report |
| Unsupervised Few-Shot Image Classification | Tiered ImageNet 5-way (5-shot) | PL-CFE | Accuracy | 64.31 | #8 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
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