Jul 2026
Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection
To minimize knowledge interference during fusion, this work presents 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.
Aoting Zhang, Dongbao Yang, Chang Liu et al.
· arXiv.org · 0 citations