Uncovering bias in the PlantVillage dataset
Mehmet Alican Noyan
Abstract
We report our investigation on the use of the popular PlantVillage dataset for training deep learning based plant disease detection models. We trained a machine learning model using only 8 pixels from the PlantVillage image backgrounds. The model achieved 49.0% accuracy on the held-out test set, well above the random guessing accuracy of 2.6%. This result indicates that the PlantVillage dataset contains noise correlated with the labels and deep learning models can easily exploit this bias to make predictions. Possible approaches to alleviate this problem are discussed.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Bias Detection | PlantVillage_8px | Accuracy (%) | 49 | RandomForest_default_hyperparameters |
Related Papers
Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations2025-07-18Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy2025-07-17Federated Learning for Commercial Image Sources2025-07-17MUPAX: Multidimensional Problem Agnostic eXplainable AI2025-07-17A Survey of Deep Learning for Geometry Problem Solving2025-07-16Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking2025-07-15Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks2025-07-14