Abstract: Highlights•We propose a novel instance-aware diversity feature generation (IDFG) framework, which transcends the limitations of solely relying on hard positive or negative samples for unsupervised person re-identification.•We introduce instance-aware masked auto-encoder that generates foreground-invariant diversity counterparts of given exemplars to alleviate the instance background interference.•We devise an instance-aware diversity feature mining module, which joints diversity-level contrastive loss to exploit the compactness and independence of clustering to update the memory dictionary.•Extensive experiments validate the superiority of our proposed IDFG compared to the star-of-the-art unsupervised ReID methods on Market1501, DukeMTMC-reID and MSMT17 datasets.
Loading