基于未来感知解耦跨头蒸馏的增量目标检测
Incremental Object Detection via Future-Aware Decoupled Cross-Head Distillation
把检测头与骨干网络的训练解耦，并用两个冻结的互补教师对学生的 ROI 特征做跨头蒸馏，可直接迁移到任何需要缓解灾难性遗忘的增量检测/分割框架中。
原文依据 we propose a decoupled training mechanism for the model's backbone and classification head
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）使人工智能系统能够持续获取新的目标类别，同时保留对先前已学类别的知识，这一能力对于在动态的真实环境中部署至关重要。现有的 IOD 方法通常依赖知识蒸馏来缓解灾难性遗忘。然而，学生模型的检测头与骨干网络之间的紧密耦合会导致蒸馏梯度在检测头处与新类别的监督信号发生冲突，从而将检测头特有的偏置注入骨干网络，最终削弱蒸馏效果。为解决这一问题，我们提出了一种针对模型骨干网络与分类头的解耦训练机制。具体而言，我们引入了未来感知解耦跨头蒸馏（FaCHD）方法，该方法利用两个冻结的互补教师（历史教师与中间教师）对学生的 ROI 特征进行解码，以执行跨头蒸馏。该策略隐式地缓解了由检测头偏置引起的预测冲突，并提供了更丰富的任务相关指导，从而提升蒸馏效率。为进一步解决检测头偏置与模型新近性问题，我们提出了原型语义漂移补偿模块，该模块重新校准旧类别的多粒度原型，有效纠正语义漂移并增强检测头的稳定性。在两个标准 IOD 基准上的大量实验证明了所提方法的有效性与优越性。
英文原文摘要 1531 字符
Incremental Object Detection (IOD) enables AI systems to continuously acquire new object classes while preserving knowledge of previously learned ones, an ability essential for deployment in dynamic, real-world environments. Existing IOD methods typically rely on knowledge distillation to mitigate catastrophic forgetting. However, the tight coupling between the student model's detection head and backbone causes distillation gradients to conflict with new-class supervision at the head, injecting head-specific bias into the backbone and ultimately weakening distillation effectiveness. To address this issue, we propose a decoupled training mechanism for the model's backbone and classification head. Specifically, we introduce the Future-aware decoupled Cross-head Distillation (FaCHD) method, which utilizes two frozen complementary teachers (historical and intermediate teachers) to decode the student's ROI features for cross-head distillation. This strategy implicitly alleviates prediction conflicts caused by detection-head bias and provides richer task-relevant guidance, thereby improving distillation efficiency. To further address the detection head bias and model recency problem, we propose a Prototype Semantic Drift Compensation module, which recalibrates multi-granularity prototypes of old classes, effectively correcting semantic drift and enhancing the stability of the detection head. Extensive experiments on two standard IOD benchmarks demonstrate the effectiveness and superiority of the proposed method.