Exploring Tradeoffs of Annotation Cost and Model Accuracy with Contrastive Learning for Yoga Pose Classification

Abstract

Yoga pose classification is critical for intelligent environments, health, and fitness applications. This study investigates resource-efficient implementations of classification models using contrastive learning frameworks, including SimCLR, MoCo, and BYOL. We evaluate their performance across varying levels of labeled data, focusing on accuracy, computational efficiency, and robustness. MoCo offers a balanced tradeoff with 87.59% accuracy at 50% labeled data, while BYOL achieves strong results with faster inference. SimCLR, suitable for real-time applications due to faster training, consumes more memory and has slower inference. We apply data augmentation and normalization in the preprocessing pipeline to enhance generalization and address challenges like limited data and class imbalance. These techniques improve the model’s resilience and learning efficiency. Our findings guide scalable, energy-efficient, user-centered yoga pose classification models for intelligent environments.

Award

Best Presentation Award

Links

code:references.bib

@inproceedings{bib:zolboo_yoga_ie2025,

author={Damiran, Zolboo and Matsui, Tomokazu and Matsuda, Yuki and Suwa, Hirohiko and Yasumoto, Keiichi},

title={Exploring Tradeoffs of Annotation Cost and Model Accuracy with Contrastive Learning for Yoga Pose Classification},

booktitle={The 21st International Conference on Intelligent Environments (IE '25)},

pages={1--8},

year={2025},

doi={10.1109/IE64880.2025.11130168},

}

https://scrapbox.io/files/68ca6e1c9edcf53fe36e42fb.png

Category

Conference

Keywords

Collaborating Organization