用分层神经坍缩检测提升增量目标检测的效率与准确率
Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection
- 基于神经坍缩机制缓解数据不平衡问题
- 利用类别层级关系提升新类识别能力
- 适合需要持续学习的新物体检测场景
近年来，基于Transformer的目标检测模型性能显著提升。然而现实世界中不断出现新物体，要求检测模型能持续学习而不发生灾难性遗忘。尽管增量目标检测（IOD）已提出应对此挑战，但现有模型仍因性能有限和推理时间过长而难以实用。本文提出一种新型IOD框架Hier-DETR：分层神经坍缩检测Transformer，通过利用神经坍缩机制应对数据不平衡问题，并结合类别标签的层次关系，实现高效且具有竞争力的性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。