Metraipolis › archive › dc_cb53740ff031

Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks? — arXiv:2609.30080

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.30080
License (as archived): CC0-1.0
Archived: 2026-10-08T06:44:41.626Z
SHA-256 of the archived text: fd3f7646bf425d99bc3dd1bf6fcdab38dc82f8a59938f1f23a8aee1a8f402925
Stable URL of this page: https://metraipolis.com/documento/dc_cb53740ff031

How to cite

Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks? — arXiv:2609.30080 — arXiv (en), https://arxiv.org/abs/2609.30080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb53740ff031 (Metraipolis archive dc_cb53740ff031, sha256 fd3f7646bf425d99bc3dd1bf6fcdab38dc82f8a59938f1f23a8aee1a8f402925)

BibTeX

@misc{dccb53740ff031,
  title = {Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks? — arXiv:2609.30080},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb53740ff031; sha256 fd3f7646bf425d99bc3dd1bf6fcdab38dc82f8a59938f1f23a8aee1a8f402925},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation segmenters such as SAM return several plausible masks for an unlabeled image, and a student trained on the wrong one inherits its errors. Choosing among them means querying a second large model or fitting a quality head to annotated masks. We show that a candidate can be judged by what it does to a frozen self-supervised backbone's features. Normalized DINOv2 patch features lie on a hypersphere, and a candidate mask splits that sphere in two. Based on this reading, we introduce SphereTrust, which scores each candidate by three properties of the split, the angular contrast between the two sides, the coverage of the foreground's appearance modes, and contact with the image frame, one for each of three common ways a mask fails, and ranks a pool in 0.55 s per image from the frozen features alone. On eight SAM and SAM3 candidate pools spanning camouflaged, salient, and dichotomous segmentation and camouflage under low light, SphereTrust exceeds the strongest evaluated external baseline on six pools by 1.7 to 9.3 percentage points in mean selected Dice. These comparisons include published selection rules and explicitly labeled adaptations of DSS and UCOD-MKD. On the two prompted camouflage pools, its mean selected Dice is within 0.1 percentage points of the candidate-derived DSS adaptation, with a lower catastrophic-error rate. Which cue carries the signal depends on the candidate pool. The same sphere also supports training. The leading candidates enter as a candidate set with their scores as priors, prototypes reorder them, and a cross-fitted second round completes the labels, raising weighted F by 4.5, 2.3, and 5.5 points over fixed-label training on the three MLLM anchor pools, with students competitive with published unsupervised methods on nineteen test sets.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30080 — 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 2026-10-08T06:09:29.906Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).