Metraipolis › archive › dc_fc7f1cd3c6cf

QFacePlacement: From Arbitrary Tensorization to Semantic Spatial Correspondence in Modern Face Verification — arXiv:2611.02505

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02505
License (as archived)
CC0-1.0
Archived
2026-11-03T11:25:22.559Z
SHA-256 of the archived text
7c0a29b3c341ca3584fd25fd5714004f2e5e509294a63741fe4f6ccd509d76f1
Stable URL of this page
https://metraipolis.com/documento/dc_fc7f1cd3c6cf

How to cite

QFacePlacement: From Arbitrary Tensorization to Semantic Spatial Correspondence in Modern Face Verification — arXiv:2611.02505 — arXiv (en), https://arxiv.org/abs/2611.02505 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc7f1cd3c6cf (Metraipolis archive dc_fc7f1cd3c6cf, sha256 7c0a29b3c341ca3584fd25fd5714004f2e5e509294a63741fe4f6ccd509d76f1)
BibTeX
@misc{dcfc7f1cd3c6cf,
  title = {QFacePlacement: From Arbitrary Tensorization to Semantic Spatial Correspondence in Modern Face Verification — arXiv:2611.02505},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02505},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc7f1cd3c6cf; sha256 7c0a29b3c341ca3584fd25fd5714004f2e5e509294a63741fe4f6ccd509d76f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02505. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantum-inspired computer vision often reshapes high-dimensional features into tensors and applies tensor-network models. In face verification, this can be misleading: modern embeddings are optimized for cosine similarity, and tensorization alone does not establish the low-rank structure needed for tensor trains or matrix-product operators (MPOs). We study model placement through two controlled interfaces. First, cross-model embedding alignment requires a 512 x 512 operator to map AdaFace embeddings into ArcFace space. Dense Ridge and Procrustes mappings remain strong, while deterministic TT-SVD and MPO compression underperform even with basis changes and low-rank residuals. At a 64K-parameter storage budget, mean directional AUC is 0.9297 for dense Ridge, 0.8952 for rank-64 SVD, 0.8685 for the best low-rank-MPO hybrid, and approximately 0.649 for raw MPO. Second, before global pooling, we construct a 7 x 7 x 7 x 7 probe-gallery correspondence tensor from local AdaFace descriptors. A geometry-aware symmetric tensor train with bond dimension 2 uses 122 trainable parameters, compared with 2,403 for a dense linear matcher, while attaining an LFW AUC of 0.9802. Yet compression does not translate into better low-false-acceptance performance: on CFP-FP, TAR at FAR = 0.001 is 0.0102 versus 0.1734 for global cosine matching, and on CPLFW it is 0.7805 versus 0.8737. These results suggest that quantum-inspired factorization is most credible when the chosen interface provides task-aligned axes and compressible structure. They also show why aggregate AUC must be assessed alongside operational low-FAR metrics.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02505 — 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 2026-11-03T11:02:37.870Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).