ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research

Gerhard Krumpl, Henning Avenhaus, Horst Possegger

Abstract

Current progress in out-of-distribution (OOD) detection is limited by the lack of large, high-quality datasets with clearly defined OOD categories across varying difficulty levels (near- to far-OOD) that support both fine- and coarse-grained computer vision tasks. To address this limitation, we introduce ICONIC-444 (Image Classification and OOD Detection with Numerous Intricate Complexities), a specialized large-scale industrial image dataset containing over 3.1 million RGB images spanning 444 classes tailored for OOD detection research. Captured with a prototype industrial sorting machine, ICONIC-444 closely mimics real-world tasks. It complements existing datasets by offering structured, diverse data suited for rigorous OOD evaluation across a spectrum of task complexities. We define four reference tasks within ICONIC-444 to benchmark and advance OOD detection research and provide baseline results for 22 state-of-the-art post-hoc OOD detection methods.
BibTeX
@misc{krumpl2026iconic,
  author = {Gerhard Krumpl and Henning Avenhaus and Horst Possegger},
  title = {{ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research}},
  year = {2026},
  eprint = {2601.10802},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.10802},
}
Figure