Conference proceeding
Continuous Learning without Forgetting for Person Re-Identification
2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.1-8
2020
Metrics
26 Record Views
Abstract
Deep learning-based person re-identification faces a scalability challenge when the target domain requires continuous learning. Service environments, such as airports, need to recognize new visitors and add new cameras over time. Training-at-once is not enough to make the model robust to new tasks and domain variations. A well-known approach is fine-tuning, which suffers forgetting problem on old tasks when learning new tasks. Joint-training can alleviate the problem but requires old datasets, which is unobtainable in some cases. Recently, Learning without forgetting (LwF) shows its ability to mitigate the problem without old datasets. This paper extends the benefit of LwF from image classification to person re-identification with further challenges. Comprehensive experiments are based on Market1501 and DukeMTMC4ReID to evaluate and benchmark LwF to other approaches. The results confirm that LwF outperforms fine-tuning in preserving old knowledge and joint-training in faster training.
Details
- Title
- Continuous Learning without Forgetting for Person Re-Identification
- Creators
- Nehemia Sugianto - Southern Cross UniversityDian Tjondronegoro (Author) - Griffith UniversityGolam Sorwar (Author) - Southern Cross University, School of Business and TourismPrithwi Chakraborty (Author) - Southern Cross UniversityElizabeth Irenne Yuwono (Author) - Southern Cross University
- Publication Details
- 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.1-8
- Publisher
- IEEE
- Identifiers
- 991012887899702368
- Academic Unit
- Faculty of Science and Engineering; School of Business and Tourism; Faculty of Business, Law and Arts; Information Technology
- Language
- English
- Resource Type
- Conference proceeding