用于域增量目标检测的正交知识刷新

中文摘要 AI 辅助

域增量目标检测（DIOD）要求模型在保留先验知识的同时不断适应新域。参数高效微调虽有前景，但存在覆盖关键过去知识、引发域间干扰和性能下降的风险。我们提出正交知识刷新（OKR）框架，通过为每个域构建独立的特定域子空间并融合进行整体决策，还提出基于梯度的正交刷新策略及拓扑感知一致性来减少干扰和语义碎片化。实验验证了OKR的优越性，在Pascal VOC和BDD100K系列上分别比最佳无范例方法的mAP高出5.6%和6.5%。

英文摘要

Domain-incremental object detection (DIOD) requires models to continually adapt to new domains while preserving prior knowledge. Recently, parameter-efficient fine-tuning offers a promising avenue, wherein a pre-trained model is frozen and a small number of learnable parameters are injected for downstream tasks. However, these methods risk overwriting critical past knowledge, triggering inter-domain interference and performance degradation. To address this challenge, we propose Orthogonal Knowledge Refreshing (OKR), a simple yet effective framework for DIOD. OKR incrementally constructs independent domain-specific subspaces via dedicated low-rank branches for each domain, which are seamlessly fused for a holistic decision, enabling conflict-free capacity expansion without domain selection during inference. To minimize knowledge interference during fusion, we present a gradient-based orthogonal refreshing strategy that projects gradient updates of new domains onto the orthogonal complement of the fused historical subspace, supporting continual adaptation without forgetting. Moreover, to mitigate semantic fragmentation across domains, we enforce topology-aware consistency, aligning the semantic structures of old and new domains. Extensive experiments validate the superiority of OKR, outperforming the best exemplar-free method by significant margins of +5.6% and +6.5% mAP on the Pascal VOC and BDD100K series, respectively.

发表机构

• Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
• Nankai University（南开大学）
• School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
• Tsinghua University（清华大学）
• Harbin Institute of Technology（哈尔滨工业大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

Accepted by ECCV 2026