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...

Full description

Saved in:
Bibliographic Details
Published in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2285 - 2294
Main Authors: Li, Wei, Zhu, Xiatian, Gong, Shaogang
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2018
Subjects:
Computational modeling
Data models
Surveillance
Training
Training data
Visualization
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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