Knowledge Distillation with Global Filters for Efficient Human Pose Estimation


Kaushik Bhargav Sivangi (University of Glasgow), Fani Deligianni (University of Glasgow)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Efficient and accurate 2D human pose estimation (2D-HPE) remains a critical challenge that must be overcome to enable its use on resource-constrained devices. This paper introduces a novel framework that synergizes knowledge distillation with Global Filter Layers (GFL) to enable efficient and scalable 2D human pose estimation. Our approach leverages the power of a high-capacity heatmap network to train a lightweight student network. This student network employs global spectral filters as an alternative to attention-based token mixer enabling lower computational complexity and higher throughput. We specifically propose this approach on coordinate classification and regression-based 2D-HPE methods owing to their higher speed compared to heatmap models. We extensively evaluate our approach on MPII dataset with both regression and coordinate classification student networks and different filter weighting strategies. While our model is lightweight, it achieves about 18% increase in throughput speed and with 89.40PCKh@0.5 accuracy closes the performance gap with large state-of-the-art 2D-HPE models.

Citation

@inproceedings{Sivangi_2024_BMVC,
author    = {Kaushik Bhargav Sivangi and Fani Deligianni},
title     = {Knowledge Distillation with Global Filters for Efficient Human Pose Estimation},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0902.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection