Intra-Camera Supervised Person Re-Identification
| Autor: | Xiangping Zhu, Pietro Morerio, Minxian Li, Xiatian Zhu, Vittorio Murino, Shaogang Gong |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry Deep learning Supervised learning Inference 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Annotation Artificial Intelligence 0103 physical sciences Pattern recognition (psychology) Scalability 0202 electrical engineering electronic engineering information engineering Identity (object-oriented programming) Unsupervised learning 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence 010306 general physics business computer Software |
| Zdroj: | International Journal of Computer Vision. 129:1580-1595 |
| ISSN: | 1573-1405 0920-5691 |
| DOI: | 10.1007/s11263-021-01440-4 |
| Popis: | Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data. This requires a tedious data collection and annotation process, leading to poor scalability in practical re-id applications. On the other hand unsupervised re-id methods do not need identity label information, but they usually suffer from much inferior and insufficient model performance. To overcome these fundamental limitations, we propose a novel person re-identification paradigm based on an idea ofindependentper-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process, significantly reducing the amount of human annotation efforts. Consequently, it gives rise to a more scalable and more feasible setting, which we callIntra-Camera Supervised (ICS)person re-id, for which we formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method. Specifically, MATE is designed for self-discovering the cross-camera identity correspondence in a per-camera multi-task inference framework. Extensive experiments demonstrate the cost-effectiveness superiority of our method over the alternative approaches on three large person re-id datasets. For example, MATE yields 88.7% rank-1 score on Market-1501 in the proposed ICS person re-id setting, significantly outperforming unsupervised learning models and closely approaching conventional fully supervised learning competitors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|