
CL
Christian Lange, Joakim Bruslund Haurum, Bingchen Zhao, Oisin Mac Aodha
· 1 min read
ResearcharXiv cs.CV
Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery
arXiv:2611.24672v1 Announce Type: new
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.
Original source
This story was published by arXiv cs.CV and written by Christian Lange, Joakim Bruslund Haurum, Bingchen Zhao, Oisin Mac Aodha. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


