Metraipolis › archive › dc_fd25cdca927d

Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric Fruit — arXiv:2610.09726

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09726
License (as archived): CC0-1.0
Archived: 2026-10-08T12:47:32.772Z
SHA-256 of the archived text: a399e06d7c051f0641acf4886f114c1b9201cbd49d15a1f6ba2d7d8c639f3fce
Stable URL of this page: https://metraipolis.com/documento/dc_fd25cdca927d

How to cite

Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric Fruit — arXiv:2610.09726 — arXiv (en), https://arxiv.org/abs/2610.09726 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd25cdca927d (Metraipolis archive dc_fd25cdca927d, sha256 a399e06d7c051f0641acf4886f114c1b9201cbd49d15a1f6ba2d7d8c639f3fce)

BibTeX

@misc{dcfd25cdca927d,
  title = {Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric Fruit — arXiv:2610.09726},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09726},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd25cdca927d; sha256 a399e06d7c051f0641acf4886f114c1b9201cbd49d15a1f6ba2d7d8c639f3fce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09726. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Estimating remaining shelf life (RSL) from images could provide affordable decision support for perishable produce, but evaluation protocols can substantially affect reported performance when repeated images are available from the same biological specimen. We use the Hass Avocado Ripening dataset, comprising 8,834 image-RSL pairs from 426 fruits across three storage regimes, to evaluate a frozen ImageNet-pretrained visual backbone with a lightweight regression head. Our contributions are threefold: we quantify the effect of observation-level versus specimen-disjoint evaluation, compare lightweight and heavier visual backbones under specimen-disjoint cross-validation, and examine their spatial attributions using Grad-CAM. Across ten observation-level random splits, the model achieves a mean RMSE of 2.37 days with a standard deviation of 0.03 days, whereas specimen-disjoint 5-fold cross-validation yields a mean RMSE of 3.12 days with a standard deviation of 0.11 days. The corresponding mean coefficient of determination is 0.553. A matched per-specimen comparison confirms higher error under specimen-disjoint evaluation, with a probability value below 0.001 across 426 specimens, showing that observation-level partitioning gives a substantially more optimistic estimate for this dataset and model configuration. Under specimen-disjoint evaluation, MobileNetV3-Small (0.93 million parameters) achieves accuracy comparable to ResNet-18 while providing substantially higher throughput, and Grad-CAM reveals differences in spatial attribution between the lightweight backbones. These results support specimen-disjoint evaluation and attribution analysis when assessing lightweight vision models for longitudinal shelf-life prediction.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09726 — 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 2026-10-08T12:18:15.404Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).