Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection
This addresses the practical limitation of incremental object detection models for real-world applications where new objects frequently appear.
The paper tackles catastrophic forgetting in incremental object detection by introducing Hier-DETR, a framework that leverages neural collapse and hierarchical class relations to achieve competitive performance with improved efficiency.
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.