In this paper, we introduce a challenging yet practical setting for person re-identification
(ReID) task, named lifelong person re-identification (LReID), which aims to continuously …

Person ReID methods always learn through a stationary domain that is fixed by the choice of
a given dataset. In many contexts (eg, lifelong learning), those methods are ineffective …

The lifelong person re-identification (LRe-ID) model retrieves a person across multiple
cameras in continuous data streams and learns new coming datasets incrementally …

Both generalized and incremental few-shot learning have to deal with three major
challenges: learning novel classes from only few samples per class, preventing catastrophic …

Deep neural networks achieve state-of-the-art and sometimes super-human performance
across a variety of domains. However, when learning tasks sequentially, the networks easily …

Deep models have shown to be vulnerable to catastrophic forgetting, a phenomenon that
the recognition performance on old data degrades when a pre-trained model is fine-tuned …

In real world, training data for person re-identification (Re-ID) is collected discretely with
spatial and temporal variations, which requires a model to incrementally learn new …

In visual search, the gallery set could be incrementally growing and added to the database
in practice. However, existing methods rely on the model trained on the entire dataset …

Human beings can quickly adapt to environmental changes by leveraging learning
experience. However, adapting deep neural networks to dynamic environments by machine …

Abstract Person re-identification (ReID), considered as a sub-problem of image retrieval, is
critical for intelligent security. The general practice is to train a deep model on images from a …