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

Key points

• 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.1
• 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.1
• 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.1
• These results support specimen-disjoint evaluation and attribution analysis when assessing lightweight vision models for longitudinal shelf-life prediction.1

Sources (1)

• [1]Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric Fruit
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 09:21 AM

  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.

Extractive summary: sentences quoted from the sources.