提出解耦提示注意力机制，提升医疗目标检测的增量学习性能
iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
- 分离实例级提示生成与提示注意力，避免背景干扰
- 在1-shot到50-shot设置下，平均提升4.8%以上检测精度
- 适用于医疗影像增量学习，尤其适合小样本场景
现有基于提示的方法在持续学习中表现优异，但其前景-背景信息紧密耦合、提示与图文令牌间注意力耦合，导致在增量医疗目标检测任务中效果受限，主要源于医学与自然图像域间的概念差异。为此，我们提出iDPA框架，包含两个核心组件：1）实例级提示生成（IPG），将细粒度实例知识从图像中解耦，生成聚焦密集预测的提示；2）解耦提示注意力（DPA），打破原有提示注意力结构，实现更直接高效的提示信息传递，降低内存占用并缓解灾难性遗忘。我们构建了13个临床、跨模态、多器官、多类别数据集，命名为 exttt{Dataset}。实验表明，iDPA在全数据、1-shot、10-shot、50-shot设置下，分别取得5.44%、4.83%、12.88%、4.59%的FAP提升，显著优于现有最先进方法。
原文摘要 · Abstract (English)
Existing prompt-based approaches have demonstrated impressive performance in continual learning, leveraging pre-trained large-scale models for classification tasks; however, the tight coupling between foreground-background information and the coupled attention between prompts and image-text tokens present significant challenges in incremental medical object detection tasks, due to the conceptual gap between medical and natural domains. To overcome these challenges, we introduce the \method~framework, which comprises two main components: 1) Instance-level Prompt Generation (\ipg), which decouples fine-grained instance-level knowledge from images and generates prompts that focus on dense predictions, and 2) Decoupled Prompt Attention (\dpa), which decouples the original prompt attention, enabling a more direct and efficient transfer of prompt information while reducing memory usage and mitigating catastrophic forgetting. We collect 13 clinical, cross-modal, multi-organ, and multi-category datasets, referred to as \dataset, and experiments demonstrate that \method~outperforms existing SOTA methods, with FAP improvements of 5.44\%, 4.83\%, 12.88\%, and 4.59\% in full data, 1-shot, 10-shot, and 50-shot settings, respectively.
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。