FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables

TL;DR

FruitProM-V2 introduces a probabilistic approach to fruit maturity estimation, modeling it as a continuous variable to improve robustness and uncertainty representation in vision-based detection.

Contribution

It proposes a novel probabilistic model that better captures maturity uncertainty and enhances robustness against label noise compared to traditional methods.

Findings

Probabilistic model maintains performance under clean labels.

Model shows improved robustness with label noise.

Uncertainty modeling aligns with annotation disagreements near stages.

Abstract

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.