面向增量目标检测的参数化提示词
Parameterized Prompt for Incremental Object Detection
把可训练提示词从「提示池」改为由神经网络参数化生成，并用融合策略约束更新，可直接迁移到增量目标检测与开放世界检测中缓解新旧类共现导致的提示混淆与灾难性遗忘。
原文依据 P^2IOD employs networks as the parameterized prompts to adaptively consolidate knowledge across tasks.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期研究表明，将可训练提示词引入预训练模型可实现有效的增量学习。然而，提示词在增量目标检测（IOD）中的应用仍缺乏探索。本研究发现，现有的基于提示池的方法假设各增量任务的类别集合互不相交，这一假设不适用于 IOD，因为它们忽略了检测中固有的共现现象。在共现场景下，先前任务中未标注的物体可能出现在当前任务的图像中，从而导致提示池混乱。本文认为，提示结构应具备跨任务的自适应整合特性，并通过受约束的更新来防止混淆与灾难性遗忘。受此启发，我们提出面向增量目标检测的参数化提示词（P^2IOD）。借助神经网络的全局演化特性，P^2IOD 以网络作为参数化提示词，从而跨任务自适应地整合知识。为约束提示结构的更新，P^2IOD 进一步引入参数化提示词融合策略。在 PASCAL VOC2007 与 MS COCO 数据集上的大量实验表明，P^2IOD 在 IOD 中行之有效，并在现有基线中取得了最优性能。
英文原文摘要 1304 字符
Recent studies have demonstrated that incorporating trainable prompts into pretrained models enables effective incremental learning. However, the application of prompts in incremental object detection (IOD) remains underexplored. Our study reveals that existing prompts-pool-based approaches assume disjoint class sets across incremental tasks, which are unsuitable for IOD as they overlook the inherent co-occurrence phenomenon in detection. In co-occurring scenarios, unlabeled objects from previous tasks may appear in current task images, leading to confusion in prompts pool. In this paper, we hold that prompt structures should exhibit adaptive consolidation properties across tasks, with constrained updates to prevent confusion and catastrophic forgetting. Motivated by this, we introduce Parameterized Prompts for Incremental Object Detection (P^2IOD). Leveraging neural networks global evolution properties, P^2IOD employs networks as the parameterized prompts to adaptively consolidate knowledge across tasks. To constrain prompts structure updates, P^2IOD further engages a parameterized prompts fusion strategy. Extensive experiments on PASCAL VOC2007 and MS COCO datasets demonstrate that P^2IOD's effectiveness in IOD and achieves the state-of-the-art performance among existing baselines.