Open World Object Detection: A Survey

TL;DR

This survey comprehensively reviews open world object detection, an emerging field that enables neural networks to recognize and learn new objects incrementally, addressing current challenges and future directions.

Contribution

It is the first extensive survey of OWOD, covering problem definitions, datasets, methods, evaluation metrics, and related areas, with a comprehensive resource archive.

Findings

Analyzes key challenges and limitations of current OWOD algorithms.

Provides a comparative study of existing OWOD methods.

Offers future research directions for OWOD development.

Abstract

Exploring new knowledge is a fundamental human ability that can be mirrored in the development of deep neural networks, especially in the field of object detection. Open world object detection (OWOD) is an emerging area of research that adapts this principle to explore new knowledge. It focuses on recognizing and learning from objects absent from initial training sets, thereby incrementally expanding its knowledge base when new class labels are introduced. This survey paper offers a thorough review of the OWOD domain, covering essential aspects, including problem definitions, benchmark datasets, source codes, evaluation metrics, and a comparative study of existing methods. Additionally, we investigate related areas like open set recognition (OSR) and incremental learning (IL), underlining their relevance to OWOD. Finally, the paper concludes by addressing the limitations and challenges faced by current OWOD algorithms and proposes directions for future research. To our knowledge, this is the first comprehensive survey of the emerging OWOD field with over one hundred references, marking a significant step forward for object detection technology. A comprehensive source code and benchmarks are archived and concluded at https://github.com/ArminLee/OWOD Review.