English

Towards Open World Detection: A Survey

Computer Vision and Pattern Recognition 2025-08-25 v1 Artificial Intelligence

Abstract

For decades, Computer Vision has aimed at enabling machines to perceive the external world. Initial limitations led to the development of highly specialized niches. As success in each task accrued and research progressed, increasingly complex perception tasks emerged. This survey charts the convergence of these tasks and, in doing so, introduces Open World Detection (OWD), an umbrella term we propose to unify class-agnostic and generally applicable detection models in the vision domain. We start from the history of foundational vision subdomains and cover key concepts, methodologies and datasets making up today's state-of-the-art landscape. This traverses topics starting from early saliency detection, foreground/background separation, out of distribution detection and leading up to open world object detection, zero-shot detection and Vision Large Language Models (VLLMs). We explore the overlap between these subdomains, their increasing convergence, and their potential to unify into a singular domain in the future, perception.

Keywords

Cite

@article{arxiv.2508.16527,
  title  = {Towards Open World Detection: A Survey},
  author = {Andrei-Stefan Bulzan and Cosmin Cernazanu-Glavan},
  journal= {arXiv preprint arXiv:2508.16527},
  year   = {2025}
}

Comments

30 pages

R2 v1 2026-07-01T05:01:58.418Z