Metraipolis › archive › dc_0b992edd883c
The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models — arXiv:2608.23634
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23634
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:30.891Z
- SHA-256 of the archived text
88238453e46743baee8f1cb8ea8604acbdd1005847644403d0b7ae93a6a99d19- Stable URL of this page
https://metraipolis.com/documento/dc_0b992edd883c
How to cite
The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models — arXiv:2608.23634 — arXiv (en), https://arxiv.org/abs/2608.23634 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0b992edd883c (Metraipolis archive dc_0b992edd883c, sha256 88238453e46743baee8f1cb8ea8604acbdd1005847644403d0b7ae93a6a99d19)
BibTeX
@misc{dc0b992edd883c,
title = {The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models — arXiv:2608.23634},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23634},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0b992edd883c; sha256 88238453e46743baee8f1cb8ea8604acbdd1005847644403d0b7ae93a6a99d19},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23634. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many few-shot adaptation methods for vision-language models classify with a convex combination of the zero-shot text prototype and the mean of the K labelled image features, with a single blending ratio routinely tuned on held-out labels, often on the test set itself. We ask what the family's own bias-variance justification invites: what is the right ratio, can it be estimated without validation data, and is finding it where the performance is? First, the ratio minimising prototype mean-squared error has a closed form whose support-set plug-in is exactly a positive-part James-Stein coefficient shrinking towards the text prototype. Across 4,800 cells (ten datasets, five backbones including SigLIP, five shot counts, five seeds, four prompt tiers) this theoretically optimal ratio is a reliable estimate of the wrong quantity: on the 950 primary-tier cells where it is defined it trails a test-set-oracle ratio by 8.5 points. It saturates near 1, discarding the text prior for a nearest-class-mean classifier, because 78% of the text-image prototype distance it treats as bias is a class-independent offset that the arg max largely cancels. We prove the mechanism and bound its share of the damage at 26% by a counterfactual. Second, leave-one-out on the support set alone sets a ratio landing within 0.9 points of the oracle blend, so it is estimable without validation data. Third, validation-free linear probes beat even the oracle-tuned blend: CLAP by +1.9 points and LP++ by +1.5 on average, and at K >= 4 all four validation-free baselines sit above the oracle, the linear probes by margins excluding zero. These results locate the ceiling in the model class, not the hyperparameter: the ratio can be set near-optimally for free, and it is still not where the performance is. Code, cached features, per-cell records: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.23634 — 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 2026-10-18T06:28:52.299Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).