超越提示词退化：原型引导的双池提示词增量目标检测
Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection
提出双池提示词解耦范式（共享池+私有池）与原型伪标签生成模块，可复用于任何基于提示词的增量目标检测器，缓解提示词耦合与漂移问题。
原文依据 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.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论增量目标检测（IOD）旨在持续学习新的目标类别而不遗忘先前学到的类别。近期，基于提示词的方法因其无需回放的设计和参数高效性而受到欢迎。然而，由于提示词耦合和提示词漂移，这些方法在持续适应过程中常常遭受提示词退化。为解决这些问题，我们提出了一种新颖的提示词解耦框架PDP。PDP创新性地设计了一种双池提示词解耦范式，该范式包含一个用于捕获任务通用知识以进行前向迁移的共享池，以及一个用于学习任务特定判别特征的私有池。该范式显式分离任务通用和任务特定的提示词，防止提示词之间的干扰并缓解提示词耦合。此外，为了抵消由不一致监督（在后续任务中旧的前景对象被当作背景）引起的提示词漂移，PDP引入了一个原型伪标签生成（PPG）模块。PPG可以在训练过程中动态更新类原型空间，并利用类原型进一步过滤有价值的伪标签，从而在整个增量过程中保持监督信号的一致性。PDP在MS-COCO（AP提升9.2%）和PASCAL VOC（AP提升3.3%）基准上达到了最优性能，突显了其在平衡稳定性和可塑性方面的潜力。代码和数据集已发布于：https://github.com/zyt95579/PDP_IOD。
英文原文摘要 1548 字符
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.