Mitigate Catastrophic Remembering via Continual Self-Paced Dual-Knowledge Purification for Noisy Lifelong Person Re-Identification

Current Lifelong Person Re-Identification (LReID) methods focus on tackling the data streams with accurate labels. When the data streams with noisy labels are given, their performance is severely degraded since the model continually remembers erroneous knowledge induced by the label noise. Moreover, the well-known issue of catastrophic forgetting in LReID is exacerbated by noisy labels, which disrupt the retention of correct knowledge from previous models. Such a practical Noisy LReID task is important but challenging, and few works have attempted to address it. In this paper, we pioneer the investigation of Noisy LReID and propose a Continual Self-Paced Dual-Knowledge Purification (CSDP) method to address the catastrophic remembering of erroneous knowledge, catastrophic forgetting of correct knowledge, and limited acquisition capacity, simultaneously. Specifically, both local distribution information and global classification results are jointly leveraged to enhance the recognition and correction of noisy labels. In addition, a self-paced learning paradigm is introduced to facilitate the progressive accumulation of reliable knowledge. Finally, a Noisy LReID benchmark is constructed to support research on this task. Extensive experimental results demonstrate that the proposed CSDP method, under comparable computational overhead, outperforms state-of-the-art methods by a large margin. Our code is available at https://github.com/zhoujiahuan1991/TPAMI-CSDP.