Towards Open World Detection: A Survey

TL;DR

This survey introduces Open World Detection as a unifying framework for various vision tasks, reviewing foundational concepts, methodologies, datasets, and recent advances towards a comprehensive perception system.

Contribution

It provides a comprehensive overview of the evolution and convergence of vision subdomains, proposing Open World Detection as a unified paradigm for perception tasks.

Findings

Open World Detection unifies class-agnostic and general detection models.

The survey highlights the convergence of multiple vision subdomains.

Future potential for a unified perception domain is discussed.

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.