Deep Learning Prototype Domains for Person Re-Identification
This addresses the problem of scalable person re-identification across diverse camera views for surveillance applications, offering a novel adaptive approach without domain adaptation.
The authors tackled person re-identification by developing a deep learning method for automatic prototype-domain discovery, which adapts to new camera views without requiring training data from target domains, and demonstrated that it outperforms most state-of-the-art supervised and unsupervised methods on CUHK-SYSU and PRW benchmarks.
Person re-identification (re-id) is the task of matching multiple occurrences of the same person from different cameras, poses, lighting conditions, and a multitude of other factors which alter the visual appearance. Typically, this is achieved by learning either optimal features or matching metrics which are adapted to specific pairs of camera views dictated by the pairwise labelled training datasets. In this work, we formulate a deep learning based novel approach to automatic prototype-domain discovery for domain perceptive (adaptive) person re-id (rather than camera pair specific learning) for any camera views scalable to new unseen scenes without training data. We learn a separate re-id model for each of the discovered prototype-domains and during model deployment, use the person probe image to select automatically the model of the closest prototype domain. Our approach requires neither supervised nor unsupervised domain adaptation learning, i.e. no data available from the target domains. We evaluate extensively our model under realistic re-id conditions using automatically detected bounding boxes with low-resolution and partial occlusion. We show that our approach outperforms most of the state-of-the-art supervised and unsupervised methods on the latest CUHK-SYSU and PRW benchmarks.