Harmonious Attention Network for Person Re-identification

Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned pe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition S. 2285 - 2294
Hauptverfasser: Li, Wei, Zhu, Xiatian, Gong, Shaogang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2018
Schlagworte:
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HA-CNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00243