MultIOD: Rehearsal-free Multihead Incremental Object Detector

TL;DR

MultIOD introduces a rehearsal-free, anchor-free incremental object detection method that effectively mitigates catastrophic forgetting using multihead architectures and transfer learning, outperforming existing methods on Pascal VOC datasets.

Contribution

It presents a novel rehearsal-free, anchor-free incremental object detection approach with multihead architecture and transfer learning to reduce catastrophic forgetting.

Findings

Outperforms state-of-the-art methods on Pascal VOC datasets.

Does not require rehearsal memory, saving model states.

Uses class-wise non-max-suppression for better detection accuracy.

Abstract

Class-Incremental learning (CIL) refers to the ability of artificial agents to integrate new classes as they appear in a stream. It is particularly interesting in evolving environments where agents have limited access to memory and computational resources. The main challenge of incremental learning is catastrophic forgetting, the inability of neural networks to retain past knowledge when learning a new one. Unfortunately, most existing class-incremental methods for object detection are applied to two-stage algorithms such as Faster-RCNN, and rely on rehearsal memory to retain past knowledge. We argue that those are not suitable in resource-limited environments, and more effort should be dedicated to anchor-free and rehearsal-free object detection. In this paper, we propose MultIOD, a class-incremental object detector based on CenterNet. Our contributions are: (1) we propose a multihead feature pyramid and multihead detection architecture to efficiently separate class representations, (2) we employ transfer learning between classes learned initially and those learned incrementally to tackle catastrophic forgetting, and (3) we use a class-wise non-max-suppression as a post-processing technique to remove redundant boxes. Results show that our method outperforms state-of-the-art methods on two Pascal VOC datasets, while only saving the model in its current state, contrary to other distillation-based counterparts.