Centroid Spectral Coupling: Implicit Alignment and Representation Diversity in Self-Supervised Learning
Self-Supervised Learning (SSL) aims to align augmented views while preserving representation diversity and preventing collapse. Existing non-contrastive methods often address these goals using multiple weighted loss terms. We introduce Centroid Spectral Coupling (CSC), a single-term SSL objective that implicitly couples view alignment, representation diversity, and collapse resistance. CSC constructs centroids from independently normalized augmented-view pairs and applies a ridge-based spectral objective to their uncentered second-moment matrix. Preserving centroid magnitudes encodes view agreement while encouraging balanced representation energy across spectral directions. We establish an exact decomposition into nonnegative alignment and spectral-imbalance components, characterize the geometry of global optima, and derive finite-loss guarantees for alignment and diversity. We also show that complete constant-output collapse is a strict saddle in normalized representation space. Experiments on CIFAR-10, CIFAR-100, and Imagenette show that CSC achieves the highest linear Top-1 accuracy among the evaluated non-contrastive methods on all three benchmarks, and the highest kNN Top-1 accuracy on both CIFAR datasets. A ridge-parameter sensitivity study reveals an empirical alignment--diversity trade-off: increasing $κ$ strengthens view alignment but reduces representation effective rank. These results show that a unified spectral objective yields competitive visual representations without explicit contrastive negatives or separately weighted alignment and diversity penalties.
Authors
- Benyamin Ghojogh (ORCID: https://orcid.org/0000-0002-9617-291X)
- Saed Moradi (ORCID: https://orcid.org/0000-0001-7081-4358)
- Paul Fieguth (ORCID: https://orcid.org/0000-0001-7260-2260)
- M. Hadi Sepanj (ORCID: https://orcid.org/0009-0005-3481-1930)
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.22158
- Primary Topic
- Domain Adaptation and Few-Shot Learning
- Type
- preprint