A Transfer Learning Approach for Diverse Motion Augmentation Under Data Scarcity

Junwon Yoon, Jeon-Seong Kang, Ha-Yoon Song, Beom-Joon Park, Kwang-Woo Jeon, Hyun-Joon Chung () and Jang-Sik Park
Additional contact information
Junwon Yoon: AI Robotics R&D Division, Korea Institute of Robotics & Technology Convergence, Pohang 37666, Republic of Korea
Jeon-Seong Kang: AI Robotics R&D Division, Korea Institute of Robotics & Technology Convergence, Pohang 37666, Republic of Korea
Ha-Yoon Song: AI Robotics R&D Division, Korea Institute of Robotics & Technology Convergence, Pohang 37666, Republic of Korea
Beom-Joon Park: AI Robotics R&D Division, Korea Institute of Robotics & Technology Convergence, Pohang 37666, Republic of Korea
Kwang-Woo Jeon: AI Robotics R&D Division, Korea Institute of Robotics & Technology Convergence, Pohang 37666, Republic of Korea
Hyun-Joon Chung: AI Robotics R&D Division, Korea Institute of Robotics & Technology Convergence, Pohang 37666, Republic of Korea
Jang-Sik Park: Unmanned System and Robotics R&D Department, LIGNex1, Gyeonggi 13488, Republic of Korea

Mathematics, 2025, vol. 13, issue 15, 1-24

Abstract: Motion-capture data provide high accuracy but are difficult to obtain, necessitating dataset augmentation. To our knowledge, no prior study has investigated few-shot generative models for motion-capture data that address both quality and diversity. We tackle the diversity loss that arises with extremely small datasets ( n ≤ 10) by applying transfer learning and continual learning to retain the rich variability of a larger pretraining corpus. To assess quality, we introduce MFMMD (Motion Feature-Based Maximum Mean Discrepancy)—a metric well-suited for small samples—and evaluate diversity with the multimodality metric. Our method embeds an Elastic Weight Consolidation (EWC)-based regularization term in the generator’s loss and then fine-tunes the limited motion-capture set. We analyze how the strength of this term influences diversity and uncovers motion-specific characteristics, revealing behavior that differs from that observed in image-generation tasks. The experiments indicate that the transfer learning pipeline improves generative performance in low-data scenarios. Increasing the weight of the regularization term yields higher diversity in the synthesized motions, demonstrating a marked uplift in motion diversity. These findings suggest that the proposed approach can effectively augment small motion-capture datasets with greater variety, a capability expected to benefit applications that rely on diverse human-motion data across modern robotics, animation, and virtual reality.

Keywords: data augmentation; few-shot learning; generative adversarial networks; transfer learning; motion capture; elastic weight consolidation (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/15/2506/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/15/2506/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:15:p:2506-:d:1717023

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().