Diverse Representation Embedding for Lifelong Person Re-Identification

arXiv:2403.16003v1 Announce Type: new
Abstract: Lifelong Person Re-Identification (LReID) aims to continuously learn from successive data streams, matching individuals across multiple cameras. The key challenge for LReID is how to effectively preserve old knowledge while learning new information incrementally. Task-level domain gaps and limited old task datasets are key factors leading to catastrophic forgetting in ReLD, which are overlooked in existing methods. To alleviate this problem, we propose a novel Diverse Representation Embedding (DRE) framework for LReID. The proposed DRE …

abstract arxiv cameras challenge cs.ai cs.cv data datasets data streams diverse domain embedding identification information key knowledge learn multiple person representation the key type