Active and semi-supervised learning for object detection with imperfect data
| Autor: | Shin Dong Kyun, Phill Kyu Rhee, Minhaz Uddin Ahmed, Enkhbayar Erdenee, Songguo Jin |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Miss rate
Computer science business.industry Cognitive Neuroscience Pedestrian detection Deep learning Imperfect data Experimental and Cognitive Psychology 02 engineering and technology Semi-supervised learning computer.software_genre Machine learning Object detection Activity recognition Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Leverage (statistics) 020201 artificial intelligence & image processing Data mining Artificial intelligence business computer Software |
| Zdroj: | Cognitive Systems Research. 45:109-123 |
| ISSN: | 1389-0417 |
| DOI: | 10.1016/j.cogsys.2017.05.006 |
| Popis: | In this paper, we address the combination of the active learning (AL) and semi-supervised (SSL) learnings, called ASSL, to leverage the strong points of the both learning paradigms for improving the performance of object detection. Considering the pros and cons of the AL and SSL learning methods, ASSL where SSL method provides the incremental improvement of semi-supervised detection performance by combining the concept of diversity imported from AL methods. The proposed method demonstrates outstanding performance compared with state-of-art methods on the challenging Caltech pedestrian detection dataset, reducing the miss rate to 12.2%, which is significantly smaller than current state-of-art. In addition, extensive experiments have been carried out using ILSVRC detection dataset and online evaluation for activity recognition. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect