Metraipolis › archive › dc_ade205744203

Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition — arXiv:2609.03995

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03995
License (as archived)
CC0-1.0
Archived
2026-10-17T01:12:14.054Z
SHA-256 of the archived text
00ea054f76264fdda61bd3bf8cc9b593bfc8fea456cc28f384182c36f5bf4098
Stable URL of this page
https://metraipolis.com/documento/dc_ade205744203

How to cite

Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition — arXiv:2609.03995 — arXiv (en), https://arxiv.org/abs/2609.03995 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ade205744203 (Metraipolis archive dc_ade205744203, sha256 00ea054f76264fdda61bd3bf8cc9b593bfc8fea456cc28f384182c36f5bf4098)
BibTeX
@misc{dcade205744203,
  title = {Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition — arXiv:2609.03995},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03995},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ade205744203; sha256 00ea054f76264fdda61bd3bf8cc9b593bfc8fea456cc28f384182c36f5bf4098},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03995. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Verifying that manufactured batches of rotary milling tools, also known as carbide burrs, conform to production order sheets remains a largely manual and error-prone quality assurance task. Automating this process with computer vision faces a critical cold-start constraint since no labelled imagery from the deployment environment is available, leaving manufacturer catalogue photography as the sole source of supervision. We investigate how far catalogue supervision can support an industrial recognition pipeline under domain shift, explicitly measuring the gap between catalogue separability and performance on held-out field photographs. Our findings reveal three key insights. First, off-the-shelf frozen feature extractors do not reliably separate the two task attributes, head shape and tooth profile, motivating targeted representation learning. Second, metric learning produces near-perfect unsupervised cluster discovery on catalogue images (adjusted Rand index 0.94--0.97), yet on field photographs under half of the accuracy gained from training survives. Third, the largest transfer gains do not come from model scale or representation complexity, but from simple changes that reduce domain sensitivity: converting images to grayscale (+0.22) and constraining retrieval against the known order sheet (+0.11). We therefore treat catalogue photography as a useful cold start rather than a deployment-ready training domain, and provide empirical baselines and an evaluation protocol for catalogue-to-field transfer in precision tool manufacturing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.03995 — 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 2026-10-17T00:28:03.019Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).