FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
For agricultural applications requiring reliable fruit maturity estimation, this work provides a more robust approach that better handles uncertainty and label noise.
The paper addresses the problem of fruit maturity estimation, which is typically treated as a multi-class classification despite being a continuous process. The authors propose a probabilistic model that predicts maturity as a latent continuous variable using a distributional detection head, achieving comparable performance under clean labels and improved robustness under label noise.
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.