Metraipolis › archive › dc_a6b0f34aa620
Shortcut Learning in a Public Grape Disease Dataset: Annotation Granularity as a Modulator, Not a Cause — arXiv:2608.20663
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20663
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:49:29.598Z
- SHA-256 of the archived text
0b518ef159b5ed994bfff5241217d79dce2fa553fd6016c6b1d602d311e93037- Stable URL of this page
https://metraipolis.com/documento/dc_a6b0f34aa620
How to cite
Shortcut Learning in a Public Grape Disease Dataset: Annotation Granularity as a Modulator, Not a Cause — arXiv:2608.20663 — arXiv (en), https://arxiv.org/abs/2608.20663 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6b0f34aa620 (Metraipolis archive dc_a6b0f34aa620, sha256 0b518ef159b5ed994bfff5241217d79dce2fa553fd6016c6b1d602d311e93037)
BibTeX
@misc{dca6b0f34aa620,
title = {Shortcut Learning in a Public Grape Disease Dataset: Annotation Granularity as a Modulator, Not a Cause — arXiv:2608.20663},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20663},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6b0f34aa620; sha256 0b518ef159b5ed994bfff5241217d79dce2fa553fd6016c6b1d602d311e93037},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20663. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Public datasets for agricultural disease detection are usually judged fit for use from reported metrics, which say nothing about whether the annotation scheme is internally consistent. On one public grape disease dataset (3288 images, 11995 boxes, 6 classes), varying model capacity, input resolution and detection paradigm yields a test-set mAP50 range comparable to seed-to-seed noise, with the bottleneck at small objects across all five architectures. The finding lies on the data side: one class is annotated at whole-leaf level (median box area 43.16% of the image) while the other five are annotated at lesion level. On 5156 cross-species images containing no grape, 65.7% of the false-positive boxes fall into that one class, an over-representation of 13.41x relative to its share of the training annotations. Counterfactual retraining establishes a causal effect of granularity on the magnitude of the shortcut: shrinking only that class's boxes cuts its cross-species false positives by 66%, and a placebo control confirms the effect is specific to the manipulated class. A manipulation in the opposite direction, with criteria registered in advance, returns a negative result: coarsening the finest class to whole-leaf level (0.57% to 40.37%), matched in box count and share of annotations and with higher in-distribution AP, still leaves its cross-species false positives at zero boxes, while the unmanipulated original class holds 50.0% of them. Annotation granularity is therefore a modulator of this shortcut, not its cause: it can amplify or attenuate a sink that already exists, but cannot create one, and what fixes the destination remains open. We also give a granularity screening statistic requiring neither images nor training, and show airborne lesion-level detection to be optically out of reach. The failure mode is invisible to in-distribution evaluation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20663 — 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 2026-10-18T10:48:13.550Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).