Lifelong Person Re-Identification (LReID) extends traditional ReID by
requiring systems to continually learn from non-overlapping datasets across
different times and locations, adapting to new identities while preserving
knowledge of previous ones. Existing approaches, either rehearsal-free or
rehearsal-based, still suffer from the problem of catastrophic forgetting since
they try to cram diverse knowledge into one fixed model. To overcome this
limitation, we introduce a novel framework AdalReID, that adopts knowledge
adapters and a parameter-free auto-selection mechanism for lifelong learning.
Concretely, we incrementally build distinct adapters to learn domain-specific
knowledge at each step, which can effectively learn and preserve knowledge
across different datasets. Meanwhile, the proposed auto-selection strategy
adaptively calculates the knowledge similarity between the input set and the
adapters. On the one hand, the appropriate adapters are selected for the inputs
to process ReID, and on the other hand, the knowledge interaction and fusion
between adapters are enhanced to improve the generalization ability of the
model. Extensive experiments are conducted to demonstrate the superiority of
our AdalReID, which significantly outperforms SOTAs by about 10$\sim$20\% mAP
on both seen and unseen domains.

Lifelong Person Re-Identification (LReID) uses a novel framework called AdalReID, featuring knowledge adapters and a parameter-free auto-selection mechanism, to overcome catastrophic forgetting and improve generalization ability by incrementally building domain-specific knowledge adapters and enhancing knowledge interaction and fusion.