Research on Extending Person Re-identification Datasets Based on Generative Adversarial Network
| Title | Research on Extending Person Re-identification Datasets Based on Generative Adversarial Network |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Liu, Yujie, Su, Yixin, Ye, Xiaozhou, Qi, Yue |
| Conference Name | 2019 Chinese Automation Congress (CAC) |
| Keywords | Cameras, Deep Learning, deep training, feature extraction, Generative Adversarial Learning, Generative Adversarial Nets, generative adversarial network, generative adversarial networks, Generators, Image color analysis, label smoothing regularization for outliers with weight algorithm, learning (artificial intelligence), Metrics, neural nets, object detection, pedestrians, pedestrians image, Person Re-ID, Person re-identification, person re-identification datasets, pubcrawl, resilience, Resiliency, Scalability, surveillance camera network, Training, Training data |
| Abstract | Person re-identification(Person Re-ID) means that images of a pedestrian from cameras in a surveillance camera network can be automatically retrieved based on one of this pedestrian's image from another camera. The appearance change of pedestrians under different cameras poses a huge challenge to person re-identification. Person re-identification systems based on deep learning can effectively extract the appearance features of pedestrians. In this paper, the feature enhancement experiment is conducted, and the result showed that the current person reidentification datasets are relatively small and cannot fully meet the need of deep training. Therefore, this paper studied the method of using generative adversarial network to extend the person re-identification datasets and proposed a label smoothing regularization for outliers with weight (LSROW) algorithm to make full use of the generated data, effectively improved the accuracy of person re-identification. |
| URL | https://ieeexplore.ieee.org/document/8996586 |
| DOI | 10.1109/CAC48633.2019.8996586 |
| Citation Key | liu_research_2019 |
- neural nets
- Training data
- Training
- surveillance camera network
- Scalability
- Resiliency
- resilience
- pubcrawl
- person re-identification datasets
- Person re-identification
- Person Re-ID
- pedestrians image
- pedestrians
- object detection
- Cameras
- Metrics
- learning (artificial intelligence)
- label smoothing regularization for outliers with weight algorithm
- Image color analysis
- Generators
- generative adversarial networks
- generative adversarial network
- Generative Adversarial Nets
- Generative Adversarial Learning
- feature extraction
- deep training
- deep learning