Continual Object Detection: A review of definitions, strategies, and challenges
It addresses the need for continual learning in object detection for applications like robotics and autonomous vehicles, but is incremental as it reviews and evaluates existing methods.
This review tackles the problem of class-incremental object detection, analyzing current strategies and evaluating them with a new metric to quantify stability and plasticity, highlighting its complexity due to unknown classes and missing annotations.
The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is 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.