# Cooperative learning of Pl@ntNet's Artificial Intelligence algorithm: how does it work and how can we improve it?

arXiv: https://arxiv.org/abs/2406.03356 · HTML: https://mlsanity.com/paper/2406.03356/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data](https://mlsanity.com/paper/2404.01413/) (2024)
- [Deep learning from crowds](https://mlsanity.com/paper/1709.01779/) (2017)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism](https://mlsanity.com/paper/2305.18438/) (2023)
- [On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification](https://mlsanity.com/paper/2203.16481/) (2022)
- [Learning from Crowds by Modeling Common Confusions](https://mlsanity.com/paper/2012.13052/) (2020)
- [Perspectives on individual animal identification from biology and computer vision](https://mlsanity.com/paper/2103.00560/) (2021)
- [Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion](https://mlsanity.com/paper/2010.12181/) (2020)
- [Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration](https://mlsanity.com/paper/2308.03172/) (2023)
- [Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification](https://mlsanity.com/paper/1803.02781/) (2018)
- [Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis](https://mlsanity.com/paper/2304.00395/) (2023)
- [Identify ambiguous tasks combining crowdsourced labels by weighting Areas Under the Margin](https://mlsanity.com/paper/2209.15380/) (2022)

## Built on by (most cited first, 4 of 4)

- [Unlocking Zero-Shot Plant Segmentation with Pl@ntNet Intelligence](https://mlsanity.com/paper/2510.12579/) (2025)
- [Estimating Individual Tree Height and Species from UAV Imagery](https://mlsanity.com/paper/2603.23669/) (2026)
- [Understanding Representation Gaps Across Scales in Tropical Tree Species Classification from Drone Imagery](https://mlsanity.com/paper/2604.23019/) (2026)
- [Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea](https://mlsanity.com/paper/2609.24064/) (2026)

## Abstract (arXiv)

Deep learning models for plant species identification rely on large annotated datasets. The PlantNet system enables global data collection by allowing users to upload and annotate plant observations, leading to noisy labels due to diverse user skills. Achieving consensus is crucial for training, but the vast scale of collected data makes traditional label aggregation strategies challenging. Existing methods either retain all observations, resulting in noisy training data or selectively keep those with sufficient votes, discarding valuable information. Additionally, as many species are rarely observed, user expertise can not be evaluated as an inter-user agreement: otherwise, botanical experts would have a lower weight in the AI training step than the average user. Our proposed label aggregation strategy aims to cooperatively train plant identification AI models. This strategy estimates user expertise as a trust score per user based on their ability to identify plant species from crowdsourced data. The trust score is recursively estimated from correctly identified species given the current estimated labels. This interpretable score exploits botanical experts' knowledge and the heterogeneity of users. Subsequently, our strategy removes unreliable observations but retains those with limited trusted annotations, unlike other approaches. We evaluate PlantNet's strategy on a released large subset of the PlantNet database focused on European flora, comprising over 6M observations and 800K users. We demonstrate that estimating users' skills based on the diversity of their expertise enhances labeling performance. Our findings emphasize the synergy of human annotation and data filtering in improving AI performance for a refined dataset. We explore incorporating AI-based votes alongside human input. This can further enhance human-AI interactions to detect unreliable observations.