Metraipolis › archive › dc_7aa2fad70e62

LIPS-PC: Learning Illumination Patterns for Single-Pixel Classification — arXiv:2611.04780

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04780
License (as archived)
CC0-1.0
Archived
2026-11-04T18:55:59.525Z
SHA-256 of the archived text
1a55e1d7a957d439b34221f4ca3016b256582d287dd561d372836f081087c384
Stable URL of this page
https://metraipolis.com/documento/dc_7aa2fad70e62

How to cite

LIPS-PC: Learning Illumination Patterns for Single-Pixel Classification — arXiv:2611.04780 — arXiv (en), https://arxiv.org/abs/2611.04780 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7aa2fad70e62 (Metraipolis archive dc_7aa2fad70e62, sha256 1a55e1d7a957d439b34221f4ca3016b256582d287dd561d372836f081087c384)
BibTeX
@misc{dc7aa2fad70e62,
  title = {LIPS-PC: Learning Illumination Patterns for Single-Pixel Classification — arXiv:2611.04780},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04780},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7aa2fad70e62; sha256 1a55e1d7a957d439b34221f4ca3016b256582d287dd561d372836f081087c384},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04780. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In single-pixel (ghost) imaging, known illumination patterns probe an object and a detector with no spatial resolution returns one number per pattern. Each measurement costs acquisition time and photons and, for ionizing probes, contributes to delivered dose. Motivated by automated radiographic defect screening, where a class label suffices, we introduce Learning Illumination Patterns for Single-Pixel Classification (LIPS-PC). The patterns are learned end-to-end while the measurement operator remains one fixed linear matrix, identical for every input. We parameterize it as a residual correction to a two-dimensional discrete cosine transform (2D-DCT), $D=D_{\mathrm{base}}+\Delta$, and jointly train the correction and a compact classifier using cross-entropy, without a reconstruction objective. This yields a task-driven linear embedding through optimization. We evaluate LIPS-PC numerically on MNIST and Fashion-MNIST under a controlled protocol, then on RIAWELC, a real industrial X-ray weld-radiograph dataset. Across five budgets, $M\in{8,16,32,64,128}$, corresponding to sampling ratios from below 1% to 12.5%, the learned operator outperforms the best tested fixed transform by 9-15 percentage points at $M=8$ on all three datasets. Its eight-measurement accuracy requires roughly 16-32 measurements with the best fixed transform, indicating a $2\times$ to $4\times$ saving at comparable accuracy. The advantage generally shrinks as $M$ increases, with a small reversal on RIAWELC at higher budgets. These results show that learning what to measure is especially valuable when measurements are scarce.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optics (physics.optics) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04780 — 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 2026-11-04T18:35:37.540Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).