Catastrophic forgetting is a critical chanllenge for incremental object detection (IOD). Most existing methods treat the detector monolithically, relying on instance replay or knowledge distillation without analyzing component-specific forgetting. Through dissection of Faster R-CNN, we reveal a key insight: Catastrophic forgetting is predominantly localized to the RoI Head classifier, while regressors retain robustness across incremental stages. This finding challenges conventional assumptions, motivating us to develop a framework termed NSGP-RePRE. Regional Prototype Replay (RePRE) mitigates classifier forgetting via replay of two types of prototypes: coarse prototypes represent class-wise semantic centers of RoI features, while fine-grained prototypes model intra-class variations. Null Space Gradient Projection (NSGP) is further introduced to eliminate prototype-feature misalignment by updating the feature extractor in directions orthogonal to subspace of old inputs via gradient projection, aligning RePRE with incremental learning dynamics. Our simple yet effective design allows NSGP-RePRE to achieve state-of-the-art performance on the Pascal VOC and MS COCO datasets under various settings. Our work not only advances IOD methodology but also provide pivotal insights for catastrophic forgetting mitigation in IOD. Code will be available soon.

翻译：灾难性遗忘是增量目标检测（IOD）面临的关键挑战。现有方法大多将检测器视为整体，依赖实例回放或知识蒸馏，而未分析组件特定的遗忘现象。通过对Faster R-CNN的剖析，我们发现关键机制：灾难性遗忘主要集中于RoI头部分类器，而回归器在增量阶段间保持稳健性。这一发现挑战了传统假设，促使我们提出名为NSGP-RePRE的框架。区域原型回放（RePRE）通过回放两类原型缓解分类器遗忘：粗粒度原型表征RoI特征的类间语义中心，细粒度原型建模类内差异。进一步引入零空间梯度投影（NSGP），通过将特征提取器的更新梯度投影至旧输入子空间的正交方向，消除原型-特征错位问题，使RePRE与增量学习动态对齐。我们简洁高效的设计使NSGP-RePRE在Pascal VOC和MS COCO数据集的各种设定下均取得最先进性能。本研究不仅推进了IOD方法学，更为IOD中灾难性遗忘的缓解提供了关键见解。代码即将开源。