Metraipolis › archive › dc_81fca9725f2a

Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling — arXiv:2610.22267

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22267
License (as archived)
CC0-1.0
Archived
2026-10-16T10:36:48.896Z
SHA-256 of the archived text
12fc01d7eb6348d38d1a36dbe5ff11e5231d68deb9f5a60ef586558590bd9fa4
Stable URL of this page
https://metraipolis.com/documento/dc_81fca9725f2a

How to cite

Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling — arXiv:2610.22267 — arXiv (en), https://arxiv.org/abs/2610.22267 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_81fca9725f2a (Metraipolis archive dc_81fca9725f2a, sha256 12fc01d7eb6348d38d1a36dbe5ff11e5231d68deb9f5a60ef586558590bd9fa4)
BibTeX
@misc{dc81fca9725f2a,
  title = {Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling — arXiv:2610.22267},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22267},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_81fca9725f2a; sha256 12fc01d7eb6348d38d1a36dbe5ff11e5231d68deb9f5a60ef586558590bd9fa4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22267. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Strong guidance in text-to-image (T2I) diffusion models concentrates sampling toward high-density modes of the conditional distribution, collapsing independently sampled noise vectors onto nearly identical visual prototypes. This limits utility for tasks that demand distributional breadth, most critically synthetic data augmentation. Diversity, however, is a collective property of the whole batch: a set can preserve every pairwise distance yet still collapse onto a low-dimensional subspace. Existing sum-of-pairwise noise-optimization and repulsion objectives respond only weakly to this higher-order failure. We propose DetNO (Determinant Noise Optimization), which formulates diverse generation as RKHS volume maximization on the initial noise, maximizing the log-determinant of an RBF Gram matrix over one-step Tweedie predictions. This set-level functional equals the squared batch volume; its repulsion is strongest when the batch is most collapsed and self-attenuates as diversity is achieved. An anchor-based fidelity term keeps the optimized noises near plausible regions, and Lagrangian relaxation gives a two-term objective with a single hyperparameter $\lambda$ governing the diversity-quality trade-off, without training or sampler modification. Across three backbones (SD1.5, SDXL, SD3), DetNO achieves leading intra-batch diversity in VendiScore and Mean Self-Similarity, and a downstream few-shot classification experiment confirms that broader mode coverage brings statistically significant accuracy gains for synthetic data augmentation in the low-shot regime. Fixing the pipeline and varying only the batch objective, both RBF-based aggregators outperform InfoNCE, and the log-determinant attains the best downstream accuracy on both benchmarks. Its diversity advantage over InfoNCE widens as the batch grows. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.22267 — 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 2026-10-16T08:52:02.729Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).