Harmonious Attention Network for Person Re-identification
- 1 June 2018
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2285-2294
- https://doi.org/10.1109/cvpr.2018.00243
Abstract
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.Keywords
This publication has 13 references indexed in Scilit:
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Person Re-Identification by Discriminative Selection in Video RankingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Partial Person Re-IdentificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Going deeper with convolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Person Re-IdentificationPublished by Springer Science and Business Media LLC ,2014
- Dorsal and Ventral Attention SystemsThe Neuroscientist, 2013
- Reidentification by Relative Distance ComparisonIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Large scale metric learning from equivalence constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- Regularized multi--task learningPublished by Association for Computing Machinery (ACM) ,2004