解决增量目标检测中提示词退化问题，提升模型持续学习能力
Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection
- 设计双池提示解耦框架，分离通用与专用提示避免干扰
- 在MS-COCO上提升9.2% AP，PASCAL VOC上提升3.3% AP
- 适合需要持续学习新类别的视觉系统开发者
增量目标检测（IOD）旨在不遗忘旧类别的情况下持续学习新类别。近期基于提示的方法因其无需重放且参数高效而受到关注，但因提示耦合与提示漂移，在持续适应中常出现提示退化。为此，本文提出新颖的提示解耦框架PDP，创新性地采用双池提示解耦机制：共享池用于捕获任务通用知识以实现前向迁移，私有池用于学习任务特定判别特征。该机制显式分离通用与专用提示，防止提示间干扰并缓解提示耦合。此外，为应对因旧前景物体在后续任务中被误标为背景导致的提示漂移问题，PDP引入原型伪标签生成（PPG）模块，动态更新类别原型空间，并利用原型筛选有价值的伪标签，保持增量过程中的监督信号一致性。PDP在MS-COCO（AP提升9.2%）和PASCAL VOC（AP提升3.3%）基准上达到当前最优性能，凸显其在稳定性和可塑性间的平衡潜力。代码与数据集已开源：https://github.com/zyt95579/PDP_IOD/tree/main
原文摘要 · Abstract (English)
Incremental Object Detection (IOD) aims to continuously learn new object categories without forgetting previously learned ones. Recently, prompt-based methods have gained popularity for their replay-free design and parameter efficiency. However, due to prompt coupling and prompt drift, these methods often suffer from prompt degradation during continual adaptation. To address these issues, we propose a novel prompt-decoupled framework called PDP. PDP innovatively designs a dual-pool prompt decoupling paradigm, which consists of a shared pool used to capture task-general knowledge for forward transfer, and a private pool used to learn task-specific discriminative features. This paradigm explicitly separates task-general and task-specific prompts, preventing interference between prompts and mitigating prompt coupling. In addition, to counteract prompt drift resulting from inconsistent supervision where old foreground objects are treated as background in subsequent tasks, PDP introduces a Prototypical Pseudo-Label Generation (PPG) module. PPG can dynamically update the class prototype space during training and use the class prototypes to further filter valuable pseudo-labels, maintaining supervisory signal consistency throughout the incremental process. PDP achieves state-of-the-art performance on MS-COCO (with a 9.2\% AP improvement) and PASCAL VOC (with a 3.3\% AP improvement) benchmarks, highlighting its potential in balancing stability and plasticity. The code and dataset are released at: https://github.com/zyt95579/PDP\_IOD/tree/main
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。