Metraipolis › archive › dc_f664eb97de10
Learning a Flow to Self-Supervised Representations — arXiv:2609.29350
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29350
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T05:26:32.364Z
- SHA-256 of the archived text
0577581b0bb26577c7cf0ec914e4ad59f41fd75a29e0904fe5f14f1b53427299- Stable URL of this page
https://metraipolis.com/documento/dc_f664eb97de10
How to cite
Learning a Flow to Self-Supervised Representations — arXiv:2609.29350 — arXiv (en), https://arxiv.org/abs/2609.29350 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f664eb97de10 (Metraipolis archive dc_f664eb97de10, sha256 0577581b0bb26577c7cf0ec914e4ad59f41fd75a29e0904fe5f14f1b53427299)
BibTeX
@misc{dcf664eb97de10,
title = {Learning a Flow to Self-Supervised Representations — arXiv:2609.29350},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29350},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f664eb97de10; sha256 0577581b0bb26577c7cf0ec914e4ad59f41fd75a29e0904fe5f14f1b53427299},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29350. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Explicit geometric references offer a direct way to structure self-supervised representations. Existing adversarial distribution-matching formulations, however, require costly encoder-critic optimization. We introduce Flow-Based Distribution Matching (FBDM), a non-adversarial framework that learns this reference-directed geometry through spherical conditional velocity regression. An ETF-inspired reference allows its number of components K' to exceed the auxiliary flow dimension d* while retaining structured geometric separation. We assign both augmented views of each image to the same target, while limiting how many images each reference center can receive. An explicit alignment loss further pulls the two views' representations closer together. Experiments across benchmarks ranging from CIFAR to ImageNet show that FBDM achieves performance nearly on par with DM and remains competitive with existing SSL methods. Matched training-cost comparisons show a 1.48- to 1.83-fold speedup over DM with a negligible increase in GPU memory usage. We also provide a theoretical explanation for the usefulness of the learned representations: under stated conditions, we bound the downstream misclassification rate in terms of the FBDM pretraining loss. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.29350 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:50:39.664Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).