Guardado en:
Detalles Bibliográficos
Autores principales: Cheppally, Rahul Harsha, Rai, Sidharth, Baral, Sudan, Vail, Benjamin, Sharda, Ajay
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.26084
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915965619404800
author Cheppally, Rahul Harsha
Rai, Sidharth
Baral, Sudan
Vail, Benjamin
Sharda, Ajay
author_facet Cheppally, Rahul Harsha
Rai, Sidharth
Baral, Sudan
Vail, Benjamin
Sharda, Ajay
contents Accurate fruit maturity identification is essential for determining harvest timing, as incorrect assessment directly affects yield and post-harvest quality. Although ripening is a continuous biological process, vision-based maturity estimation is typically formulated as a multi-class classification task, which imposes sharp boundaries between visually similar stages. To examine this limitation, we perform an annotation reliability study with two independent annotators on a held-out tomato dataset and observe disagreement concentrated near adjacent maturity stages. Motivated by this observation, we model maturity as a latent continuous variable and predict it probabilistically using a distributional detection head, converting the distribution into class probabilities through the cumulative distribution function (CDF). The proposed formulation maintains comparable performance to a standard detector under clean labels while better representing uncertainty. Furthermore, when controlled label noise is introduced during training, the probabilistic model demonstrates improved robustness relative to the baseline, indicating that explicitly modeling maturity uncertainty leads to more reliable visual maturity estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26084
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
Cheppally, Rahul Harsha
Rai, Sidharth
Baral, Sudan
Vail, Benjamin
Sharda, Ajay
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
Accurate fruit maturity identification is essential for determining harvest timing, as incorrect assessment directly affects yield and post-harvest quality. Although ripening is a continuous biological process, vision-based maturity estimation is typically formulated as a multi-class classification task, which imposes sharp boundaries between visually similar stages. To examine this limitation, we perform an annotation reliability study with two independent annotators on a held-out tomato dataset and observe disagreement concentrated near adjacent maturity stages. Motivated by this observation, we model maturity as a latent continuous variable and predict it probabilistically using a distributional detection head, converting the distribution into class probabilities through the cumulative distribution function (CDF). The proposed formulation maintains comparable performance to a standard detector under clean labels while better representing uncertainty. Furthermore, when controlled label noise is introduced during training, the probabilistic model demonstrates improved robustness relative to the baseline, indicating that explicitly modeling maturity uncertainty leads to more reliable visual maturity estimation.
title FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2604.26084