Scene adaptive crowd counting
| dc.contributor.author | Krishna Reddy, Mahesh Kumar | |
| dc.contributor.examiningcommittee | Leung, Carson (Computer Science) | en_US |
| dc.contributor.examiningcommittee | Hossain, Ekram (Electrical and Computer Engineering) | en_US |
| dc.contributor.supervisor | Wang, Yang (Computer Science) | en_US |
| dc.date.accessioned | 2020-05-01T15:46:24Z | |
| dc.date.available | 2020-05-01T15:46:24Z | |
| dc.date.copyright | 2020-04-15 | |
| dc.date.issued | 2020-04 | en_US |
| dc.date.submitted | 2020-04-15T22:22:26Z | en_US |
| dc.degree.discipline | Computer Science | en_US |
| dc.degree.level | Master of Science (M.Sc.) | en_US |
| dc.description.abstract | We consider the problem of scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled/unlabeled images. The solution to this problem has potential applications in numerous real-world scenarios that require deploying a crowd counting model specially adapted to a target camera. In this thesis, we propose two novel methods for scene adaptive crowd counting. First, inspired by the recently introduced learning to learn paradigm in the context of few-shot regime, we aim to learn the parameters of a crowd counting model in a way to facilitate fast adaptation to the target scene. Second, we introduce a new problem called unlabeled scene adaptive crowd counting. More specifically, we propose to use few unlabeled images from the target scene to perform the adaptation. We introduce a novel AdaCrowd framework to solve this problem and it consists of a crowd counting network and a guiding network. The guiding network predicts some parameters in the crowd counting network based on the unlabeled images from a particular scene. This allows our model to adapt to different target scenes. The experimental results on several challenging benchmark datasets demonstrate the effectiveness of our two proposed approaches. | en_US |
| dc.description.note | October 2020 | en_US |
| dc.identifier.citation | Reddy, M. K. K., Hossain, M., Rochan, M., & Wang, Y. (2020). Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning. In The IEEE Winter Conference on Applications of Computer Vision (pp. 2814-2823). | en_US |
| dc.identifier.uri | http://hdl.handle.net/1993/34677 | |
| dc.language.iso | eng | en_US |
| dc.rights | open access | en_US |
| dc.subject | Computer Science | en_US |
| dc.subject | Computer Vision | en_US |
| dc.subject | Machine Learning | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Crowd Counting | en_US |
| dc.title | Scene adaptive crowd counting | en_US |
| dc.type | master thesis | en_US |