DeepAI AI Chat
Log In Sign Up

Unsupervised Tracklet Person Re-Identification

by   Minxian Li, et al.
Queen Mary University of London

Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in a practical re-id deployment, due to the lack of exhaustive identity labelling of positive and negative image pairs for every camera-pair. In this work, we present an unsupervised re-id deep learning approach. It is capable of incrementally discovering and exploiting the underlying re-id discriminative information from automatically generated person tracklet data end-to-end. We formulate an Unsupervised Tracklet Association Learning (UTAL) framework. This is by jointly learning within-camera tracklet discrimination and cross-camera tracklet association in order to maximise the discovery of tracklet identity matching both within and across camera views. Extensive experiments demonstrate the superiority of the proposed model over the state-of-the-art unsupervised learning and domain adaptation person re-id methods on eight benchmarking datasets.


page 4

page 5

page 6

page 9

page 12


Unsupervised Person Re-identification by Deep Learning Tracklet Association

Mostexistingpersonre-identification(re-id)methods relyon supervised mode...

Unsupervised Noisy Tracklet Person Re-identification

Existing person re-identification (re-id) methods mostly rely on supervi...

Deep Association Learning for Unsupervised Video Person Re-identification

Deep learning methods have started to dominate the research progress of ...

Deep Learning Prototype Domains for Person Re-Identification

Person re-identification (re-id) is the task of matching multiple occurr...

Camera Adversarial Transfer for Unsupervised Person Re-Identification

Unsupervised person re-identification (Re-ID) methods consist of trainin...

Weakly Supervised Tracklet Person Re-Identification by Deep Feature-wise Mutual Learning

The scalability problem caused by the difficulty in annotating Person Re...

Temporal Continuity Based Unsupervised Learning for Person Re-Identification

Person re-identification (re-id) aims to match the same person from imag...