A Practical Hybrid Active Learning Approach for Human Pose Estimation
Kaplan, Sinan; Juvonen, Joni; Lensu, Lasse (2021-04-10)
Post-print / Final draft
Kaplan, Sinan
Juvonen, Joni
Lensu, Lasse
10.04.2021
Springer, Cham
School of Engineering Science
Kaikki oikeudet pidätetään.
© Springer Nature Switzerland AG 2021
© Springer Nature Switzerland AG 2021
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2021050629042
https://urn.fi/URN:NBN:fi-fe2021050629042
Tiivistelmä
Active learning (AL) has not received much attention in deep learning (DL) for human pose estimation. In this paper, a practical hybrid active learning strategy is proposed for training a human pose estimation model, and it is tested in an industrial online environment. The conducted experiments show that the active learning strategy to select diverse samples to be annotated outperforms the baseline method with random sampling. As a result, the strategy enables a significant improvement in the performance of pose estimation.
Lähdeviite
Kaplan, S., Juvonen, J., Lensu, L. (2021). A Practical Hybrid Active Learning Approach for Human Pose Estimation. In: Torsello, A., Rossi, L., Pelillo, M., Biggio, B., Robles-Kelly, A. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2021. Lecture Notes in Computer Science, vol 12644. Springer, Cham. DOI: 10.1007/978-3-030-73973-7_32
Kokoelmat
- Tieteelliset julkaisut [1212]