Spatial-Aware GAN for Unsupervised Person Re-identification
arXiv:1911.11312
Abstract
The recent person re-identification research has achieved great success by learning from a large number of labeled person images. On the other hand, the learned models often experience significant performance drops when applied to images collected in a different environment. Unsupervised domain adaptation (UDA) has been investigated to mitigate this constraint, but most existing systems adapt images at pixel level only and ignore obvious discrepancies at spatial level. This paper presents an innovative UDA-based person re-identification network that is capable of adapting images at both spatial and pixel levels simultaneously. A novel disentangled cycle-consistency loss is designed which guides the learning of spatial-level and pixel-level adaptation in a collaborative manner. In addition, a novel multi-modal mechanism is incorporated which is capable of generating images of different geometry views and augmenting training images effectively. Extensive experiments over a number of public datasets show that the proposed UDA network achieves superior person re-identification performance as compared with the state-of-the-art.
Accepted to ICPR2020
References in corpus (10)
- Learning Transferable Features with Deep Adaptation Networks
- Unsupervised Domain Adaptation by Backpropagation
- Person Re-identification: Past, Present and Future
- Random Erasing Data Augmentation
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Domain Separation Networks
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation
- Scene Text Synthesis for Efficient and Effective Deep Network Training
- Towards Realistic 3D Embedding via View Alignment
- EMLight: Lighting Estimation via Spherical Distribution Approximation