Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection

TL;DR

This paper introduces Hier-DETR, a transformer-based framework for incremental object detection that leverages Neural Collapse and hierarchical class relations to improve efficiency and performance in continual learning scenarios.

Contribution

The paper proposes a novel Hierarchical Neural Collapse Detection Transformer (Hier-DETR) for class incremental object detection, addressing efficiency and performance limitations of existing models.

Findings

Achieves competitive detection performance in incremental learning.

Reduces inference time compared to existing methods.

Effectively handles class imbalance with Neural Collapse.

Abstract

Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without suffering from catastrophic forgetting. Although Incremental Object Detection (IOD) has emerged to address this challenge, these existing models are still not practical due to their limited performance and prolonged inference time. In this paper, we introduce a novel framework for IOD, called Hier-DETR: Hierarchical Neural Collapse Detection Transformer, ensuring both efficiency and competitive performance by leveraging Neural Collapse for imbalance dataset and Hierarchical relation of classes' labels.