# Uncovering bias in the PlantVillage dataset

arXiv: https://arxiv.org/abs/2206.04374 · HTML: https://mlsanity.com/paper/2206.04374/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 4 of 4)

- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Using Deep Learning for Image-Based Plant Disease Detection](https://mlsanity.com/paper/1604.03169/) (2016)
- [An open access repository of images on plant health to enable the development of mobile disease diagnostics](https://mlsanity.com/paper/1511.08060/) (2015)
- [A Deeper Look at Dataset Bias](https://mlsanity.com/paper/1505.01257/) (2015)

## Built on by (most cited first, 3 of 3)

- [FruitEnsemble: MLLM-Guided Arbitration for Heterogeneous ensemble in Fine-Grained Fruit Recognition](https://mlsanity.com/paper/2605.20892/) (2026)
- [A Dataset-Centric Benchmark of Deep Learning Methods for Grape Leaf Disease Classification and Detection](https://mlsanity.com/paper/2608.20608/) (2026)
- [Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric Fruit](https://mlsanity.com/paper/2610.09726/) (2026)

## Abstract (arXiv)

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.