Continual Object Detection: A review of definitions, strategies, and challenges

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. The efforts of researchers have been mainly focused on incremental classification tasks. Yet, we believe that continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is also more complex than conventional classification, given the occurrence of instances of classes that are unknown at the time but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations and conflicts with the background label. In this review, we analyze the current strategies proposed to tackle the problem of class-incremental object detection. Our main contributions are: (1) a short and systematic review of the methods that propose solutions to traditional incremental object detection scenarios; (2) A comprehensive evaluation of the existing approaches using a new metric to quantify the stability and plasticity of each technique in a standard way; (3) an overview of the current trends within continual object detection and a discussion of possible future research directions.

Automated summary

Continual learning focuses on learning consecutive tasks without losing performance on previously learned tasks. While most research has been on incremental classification tasks, continual object detection deserves more attention due to its wide range of applications. It is more complex than traditional classification, with instances of unknown classes appearing in subsequent tasks, resulting in missing annotations and conflicts with background labels.