Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning

Souvik Maji, Rhythm Baghel, Pratik Mazumder
Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling, PMLR 326:356-386, 2026.

Abstract

Few-shot learning helps models perform effectively in scenarios with very few labeled samples per class. Semi-supervised FSL enables the use of abundant unlabeled samples, which are cheap to collect and can improve performance. Some of the recent methods for this setting rely on clustering to generate pseudo-labels for the unlabeled samples. Since the effectiveness of clustering heavily influences the labeling of the unlabeled samples, it can significantly affect the few-shot learning performance. In this paper, we focus on improving the representation learned by the model in order to improve the clustering and, consequently, the model performance. We propose an approach for semi-supervised few-shot learning that performs a class-variance optimized clustering coupled with a cluster separation tuner in order to improve the effectiveness of clustering the labeled and unlabeled samples in this setting. It also optimizes the clustering-based pseudo-labeling process using a restricted pseudo-labeling approach and performs semantic information injection in order to improve the semi-supervised few-shot learning performance of the model. Experiments show our method outperforms recent state-of-the-art methods on benchmark datasets and remains robust under domain shifts and open-set settings with distractor classes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v326-maji26a, title = {Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning}, author = {Maji, Souvik and Baghel, Rhythm and Mazumder, Pratik}, booktitle = {Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling}, pages = {356--386}, year = {2026}, editor = {Pouplin, Alison and Vadgama, Sharvaree and Bekkers, Erik and Kaba, Sékou-Oumar and Lawrence, Hannah and Lecha, Manuel and Baker, Elizabeth and Suk, Julian and Walters, Robin and Tomczak, Jakub and Jegelka, Stefanie}, volume = {326}, series = {Proceedings of Machine Learning Research}, month = {26 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v326/main/assets/maji26a/maji26a.pdf}, url = {https://proceedings.mlr.press/v326/maji26a.html}, abstract = {Few-shot learning helps models perform effectively in scenarios with very few labeled samples per class. Semi-supervised FSL enables the use of abundant unlabeled samples, which are cheap to collect and can improve performance. Some of the recent methods for this setting rely on clustering to generate pseudo-labels for the unlabeled samples. Since the effectiveness of clustering heavily influences the labeling of the unlabeled samples, it can significantly affect the few-shot learning performance. In this paper, we focus on improving the representation learned by the model in order to improve the clustering and, consequently, the model performance. We propose an approach for semi-supervised few-shot learning that performs a class-variance optimized clustering coupled with a cluster separation tuner in order to improve the effectiveness of clustering the labeled and unlabeled samples in this setting. It also optimizes the clustering-based pseudo-labeling process using a restricted pseudo-labeling approach and performs semantic information injection in order to improve the semi-supervised few-shot learning performance of the model. Experiments show our method outperforms recent state-of-the-art methods on benchmark datasets and remains robust under domain shifts and open-set settings with distractor classes.} }
Endnote
%0 Conference Paper %T Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning %A Souvik Maji %A Rhythm Baghel %A Pratik Mazumder %B Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling %C Proceedings of Machine Learning Research %D 2026 %E Alison Pouplin %E Sharvaree Vadgama %E Erik Bekkers %E Sékou-Oumar Kaba %E Hannah Lawrence %E Manuel Lecha %E Elizabeth Baker %E Julian Suk %E Robin Walters %E Jakub Tomczak %E Stefanie Jegelka %F pmlr-v326-maji26a %I PMLR %P 356--386 %U https://proceedings.mlr.press/v326/maji26a.html %V 326 %X Few-shot learning helps models perform effectively in scenarios with very few labeled samples per class. Semi-supervised FSL enables the use of abundant unlabeled samples, which are cheap to collect and can improve performance. Some of the recent methods for this setting rely on clustering to generate pseudo-labels for the unlabeled samples. Since the effectiveness of clustering heavily influences the labeling of the unlabeled samples, it can significantly affect the few-shot learning performance. In this paper, we focus on improving the representation learned by the model in order to improve the clustering and, consequently, the model performance. We propose an approach for semi-supervised few-shot learning that performs a class-variance optimized clustering coupled with a cluster separation tuner in order to improve the effectiveness of clustering the labeled and unlabeled samples in this setting. It also optimizes the clustering-based pseudo-labeling process using a restricted pseudo-labeling approach and performs semantic information injection in order to improve the semi-supervised few-shot learning performance of the model. Experiments show our method outperforms recent state-of-the-art methods on benchmark datasets and remains robust under domain shifts and open-set settings with distractor classes.
APA
Maji, S., Baghel, R. & Mazumder, P.. (2026). Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning. Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling, in Proceedings of Machine Learning Research 326:356-386 Available from https://proceedings.mlr.press/v326/maji26a.html.

Related Material