Re-Identification with Consistent Attentive Siamese Networks
arXiv:1811.07487
Abstract
We propose a new deep architecture for person re-identification (re-id). While re-id has seen much recent progress, spatial localization and view-invariant representation learning for robust cross-view matching remain key, unsolved problems. We address these questions by means of a new attention-driven Siamese learning architecture, called the Consistent Attentive Siamese Network. Our key innovations compared to existing, competing methods include (a) a flexible framework design that produces attention with only identity labels as supervision, (b) explicit mechanisms to enforce attention consistency among images of the same person, and (c) a new Siamese framework that integrates attention and attention consistency, producing principled supervisory signals as well as the first mechanism that can explain the reasoning behind the Siamese framework's predictions. We conduct extensive evaluations on the CUHK03-NP, DukeMTMC-ReID, and Market-1501 datasets and report competitive performance.
arXiv comment10 pages, 8 figures, 3 tables, to appear in CVPR 2019
References in corpus (10)
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Person Re-identification: Past, Present and Future
- Pedestrian Alignment Network for Large-scale Person Re-identification
- Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
- Harmonious Attention Network for Person Re-Identification
- Beyond triplet loss: a deep quadruplet network for person re-identification
- HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
- Attention-Aware Compositional Network for Person Re-identification
- Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association