Plant identification in an open-world (LifeCLEF 2016)

2025-09-25

AI Summary

This study addresses open-world plant identification, formalizing it as an open-set recognition problem for the first time to mitigate false positives caused by unknown species in real-world biodiversity monitoring. We focus on the large-scale fine-grained classification task of 1,000 Western European plant species from LifeCLEF 2016. Our method integrates deep learning classifiers, open-set recognition algorithms, and feature-space rejection mechanisms, trained and evaluated on over 110,000 multi-source participatory-sensing images. Key contributions are: (1) establishing a novel open-set recognition paradigm for plant identification; (2) empirically validating the effectiveness of diverse rejection strategies under realistic fine-grained conditions; and (3) introducing the first open-set benchmark and systematic analysis for plant recognition, revealing substantial performance disparities across methods in rejecting unknown classes—thereby laying a foundation for robust bio-recognition research.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Medical and Biological Imaging

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The LifeCLEF plant identification challenge aims at evaluating plant identification methods and systems at a very large scale, close to the conditions of a real-world biodiversity monitoring scenario. The 2016-th edition was actually conducted on a set of more than 110K images illustrating 1000 plant species living in West Europe, built through a large-scale participatory sensing platform initiated in 2011 and which now involves tens of thousands of contributors. The main novelty over the previous years is that the identification task was evaluated as an open-set recognition problem, i.e. a problem in which the recognition system has to be robust to unknown and never seen categories. Beyond the brute-force classification across the known classes of the training set, the big challenge was thus to automatically reject the false positive classification hits that are caused by the unknown classes. This overview presents more precisely the resources and assessments of the challenge, summarizes the approaches and systems employed by the participating research groups, and provides an analysis of the main outcomes.

Problem

• Evaluating plant identification methods at large scale for biodiversity monitoring
• Addressing open-set recognition with unknown plant species categories
• Automatically rejecting false positive classifications from unseen plant classes

Innovation

• Open-set recognition for unknown species rejection
• Large-scale participatory sensing with 110K images
• Robust plant identification using 1000 West European species