Cross Domain Residual Transfer Learning for Person Re-Identification
| Autor: | Furqan M. Khan, Francois Bremond |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
Computer science business.industry Feature extraction Contrast (statistics) 020207 software engineering 02 engineering and technology Residual Machine learning computer.software_genre Domain (software engineering) Metric (mathematics) 0202 electrical engineering electronic engineering information engineering Task analysis 020201 artificial intelligence & image processing Artificial intelligence Transfer of learning business computer |
| Zdroj: | WACV |
| DOI: | 10.1109/wacv.2019.00219 |
| Popis: | This paper presents a novel way to transfer model weights from one domain to another using residual learning framework instead of direct fine-tuning. It also argues for hybrid models that use learned (deep) features and statistical metric learning for multi-shot person re-identification when training sets are small. This is in contrast to popular end-to-end neural network based models or models that use hand-crafted features with adaptive matching models (neural nets or statistical metrics). Our experiments demonstrate that a hybrid model with residual transfer learning can yield significantly better re-identification performance than an end-to-end model when training set is small. On iLIDS-VID and PRID datasets, we achieve rank-1 recognition rates of 89.8% and 95%, respectively, which is a significant improvement over state-of-the-art. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|