Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation
Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation
In object re-identification (ReID), the development of deep learning techniques often involves model updates and deployment. It is unbearable to re-embedding and re-index with the system suspended when deploying new models. Therefore, backward-compatible representation is proposed to enable ``new'' features to be compared with ``old'' features directly, which means that …