cs.CVNov 18, 2026

Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery

Authors: Christian Lange, Joakim Bruslund Haurum, Bingchen Zhao, Oisin Mac Aodha

Organizations: University of Edinburgh · University of Southern Denmark

Abstract

Widely used category discovery benchmarks have become increasingly saturated and often fail to reflect real-world discovery settings, making long-term evaluation of new methods difficult. We introduce PS-SPLIT, a large-scale fine-grained benchmark for category discovery, motivated by taxonomic splitting: the real-world process by which what was once considered a single species is found to comprise multiple distinct ones. PS-SPLIT contains 79K globally distributed, high-quality, community-collected bird images spanning 771 species, derived from 257 recent real expert-verified taxonomic splits, with associated geographic metadata and full taxonomic hierarchy. The visual differences between categories arising from real taxonomic splits can be very subtle, often requiring significant human expertise to tell apart, making PS-SPLIT a challenging benchmark which we hope will assist in advancing fine-grained category discovery research. Based on taxonomic splitting, we introduce the task of discovery by category splitting, where the goal is to determine which known categories should be subdivided into new finer-grained subcategories. We adapt four generalized category discovery methods to this setting, evaluate existing methods, and show that there is substantial room for future progress.

Figures & tables

Appendix figures & tables27 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery

    Apr 27, 2026Jiawei Wang, Ming Lei, Yaning Yang +8Retrieval-Augmented ClassificationAI-Assisted Scientific Research

  2. RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs

    Mar 27, 2026Logan Lawrence, Mustafa Chasmai, Rangel Daroya +8Fine-Grained Image ClassificationMultimodal Model Evaluation

  3. WoodBR-Cross: A public wood-image dataset and individual-tree-disjoint benchmark for species identification

    Oct 8, 2026Daniel Casanova, Alexandre Bahia Gontijo, Arnaldo Candido Junior +2Tree Species Classification