MR-GDINO: Efficient Open-World Continual Object Detection

TL;DR

This paper introduces MR-GDINO, a scalable method for open-world continual object detection that effectively mitigates forgetting of seen, new, and unseen classes, advancing the capabilities of detection models in dynamic environments.

Contribution

It proposes a new open-world continual object detection benchmark and a novel memory-based method, MR-GDINO, to address catastrophic forgetting in unseen categories.

Findings

MR-GDINO significantly reduces forgetting of unseen classes.

The method achieves state-of-the-art performance with minimal additional parameters.

Existing detectors suffer from severe forgetting, which MR-GDINO effectively mitigates.

Abstract

Open-world (OW) recognition and detection models show strong zero- and few-shot adaptation abilities, inspiring their use as initializations in continual learning methods to improve performance. Despite promising results on seen classes, such OW abilities on unseen classes are largely degenerated due to catastrophic forgetting. To tackle this challenge, we propose an open-world continual object detection task, requiring detectors to generalize to old, new, and unseen categories in continual learning scenarios. Based on this task, we present a challenging yet practical OW-COD benchmark to assess detection abilities. The goal is to motivate OW detectors to simultaneously preserve learned classes, adapt to new classes, and maintain open-world capabilities under few-shot adaptations. To mitigate forgetting in unseen categories, we propose MR-GDINO, a strong, efficient and scalable baseline via memory and retrieval mechanisms within a highly scalable memory pool. Experimental results show that existing continual detectors suffer from severe forgetting for both seen and unseen categories. In contrast, MR-GDINO largely mitigates forgetting with only 0.1% activated extra parameters, achieving state-of-the-art performance for old, new, and unseen categories.