Pair-based Uncertainty and Diversity Promoting Early Active Learning for Person Re-identification
| Autor: | Wenhe Liu, Dinh Phung, Xiaoqin Zhang, Alexander G. Hauptmann, Ling Chen, Yi Yang, Xiaojun Chang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Active learning (machine learning)
business.industry Computer science Sample (statistics) 02 engineering and technology Machine learning computer.software_genre Representativeness heuristic Theoretical Computer Science Annotation Resource (project management) Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Pairwise comparison Artificial intelligence business computer 0801 Artificial Intelligence and Image Processing 0806 Information Systems Diversity (business) |
| Zdroj: | ACM Transactions on Intelligent Systems and Technology. 11:1-15 |
| ISSN: | 2157-6912 2157-6904 |
| Popis: | The effective training of supervised Person Re-identification (Re-ID) models requires sufficient pairwise labeled data. However, when there is limited annotation resource, it is difficult to collect pairwise labeled data. We consider a challenging and practical problem called Early Active Learning, which is applied to the early stage of experiments when there is no pre-labeled sample available as references for human annotating. Previous early active learning methods suffer from two limitations for Re-ID. First, these instance-based algorithms select instances rather than pairs, which can result in missing optimal pairs for Re-ID. Second, most of these methods only consider the representativeness of instances, which can result in selecting less diverse and less informative pairs. To overcome these limitations, we propose a novel pair-based active learning for Re-ID. Our algorithm selects pairs instead of instances from the entire dataset for annotation. Besides representativeness, we further take into account the uncertainty and the diversity in terms of pairwise relations. Therefore, our algorithm can produce the most representative, informative, and diverse pairs for Re-ID data annotation. Extensive experimental results on five benchmark Re-ID datasets have demonstrated the superiority of the proposed pair-based early active learning algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|