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
Computer scienceDiscriminative modelArtificial intelligenceConvolutional neural networkFeature learningMinimum bounding boxFeature (linguistics)Bounding overwatchMatching (statistics)Identification (biology)Machine learningPattern recognition (psychology)Feature extractionRepresentation (politics)Attention networkComputer visionImage (mathematics)
Affiliated Institutions
Related Publications
Learning Deep Features for Discriminative Localization
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable...
Deep Learning for Person Re-Identification: A Survey and Outlook
Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing dem...
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting...
Learning to rank in person re-identification with metric ensembles
We propose an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets ...
RGB-D Object Recognition via Incorporating Latent Data Structure and Prior Knowledge
For the task of RGB-D object recognition, it is important to identify suitable representations of images, which can boost the performance of object recognition. In this work, we...
Publication Info
- Year
- 2018
- Type
- preprint
- Citations
- 1377
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1377
OpenAlex
Cite This
Wei Li,
Xiatian Zhu,
Shaogang Gong
(2018).
Harmonious Attention Network for Person Re-identification.
.
https://doi.org/10.1109/cvpr.2018.00243
Identifiers
- DOI
- 10.1109/cvpr.2018.00243