Supercm: Revisiting Clustering for Semi-Supervised Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916817379786752 |
|---|---|
| author | Singh, Durgesh Boubekki, Ahcene Jenssen, Robert Kampffmeyer, Michael C. |
| author_facet | Singh, Durgesh Boubekki, Ahcene Jenssen, Robert Kampffmeyer, Michael C. |
| contents | The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach. We demonstrate that the proposed model improves the performance over the supervised-only baseline and show that our framework can be used in conjunction with other SSL methods to further boost their performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23824 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Supercm: Revisiting Clustering for Semi-Supervised Learning Singh, Durgesh Boubekki, Ahcene Jenssen, Robert Kampffmeyer, Michael C. Machine Learning Computer Vision and Pattern Recognition The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach. We demonstrate that the proposed model improves the performance over the supervised-only baseline and show that our framework can be used in conjunction with other SSL methods to further boost their performance. |
| title | Supercm: Revisiting Clustering for Semi-Supervised Learning |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23824 |