Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion
Abstract: Face detectors are becoming a crucial component of many applications, including surveillance, that often have to run on edge devices with limited processing power and memory. Therefore, there's a pressing demand for compact face detection models that can function efficiently across resource-constrained devices. Over recent years, network pruning techniques have attracted a lot of attention from researchers. These methods haven't been well examined in the context of face detectors, despite their expanding popularity. In this paper, we implement filter pruning on two already small and compact face detectors, named EXTD (Extremely Tiny Face Detector) and EResFD (Efficient ResNet Face Detector). The main pruning algorithm that we utilize is Filter Pruning via Geometric Median (FPGM), combined with the Soft Filter Pruning (SFP) iterative procedure. We also apply L1 Norm pruning, as a baseline to compare with the proposed approach. The experimental evaluation on the WIDER FACE dataset indicates that the proposed approach has the potential to further reduce the model size of already lightweight face detectors, with limited accuracy loss, or even with small accuracy gain for low pruning rates.
- Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 2021.
- RetinaFace: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641, 2019.
- Structured pruning of LSTMs via eigenanalysis and Geometric Median for mobile multimedia and deep learning applications. In 2020 IEEE International Symposium on Multimedia (ISM), pages 122–126, 2020.
- Sample and computation redistribution for efficient face detection. arXiv preprint arXiv:2105.04714, 2021.
- Soft filter pruning for accelerating deep convolutional neural networks. arXiv preprint arXiv:1808.06866, 2018.
- Filter pruning via Geometric Median for deep convolutional neural networks acceleration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
- Lffd: A light and fast face detector for edge devices. arXiv preprint arXiv:1904.10633, 2019.
- Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
- EResFD: Rediscovery of the effectiveness of standard convolution for lightweight face detection. arXiv preprint arXiv:2204.01209, 2022.
- Face detection techniques: a review. Artificial Intelligence Review, 52(2):927–948, 2019.
- Pruning filters with L1-norm and capped L1-norm for CNN compression. Applied Intelligence, 2021.
- Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710, 2016.
- DSFD: dual shot face detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5060–5069, 2019.
- PruneFaceDet: Pruning lightweight face detection network by sparsity training. In Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition, ICCPR ’20, page 181–186, New York, NY, USA, 2021. Association for Computing Machinery.
- SSD: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pages 21–37. Springer, 2016.
- ThiNet: A filter level pruning method for deep neural network compression. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
- Microsoft. Neural Network Intelligence library, https://github.com/microsoft/nni, 2021.
- Going deeper into face detection: A survey. arXiv preprint arXiv:2103.14983, 2021.
- Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
- YOLO5Face: Why reinventing a face detector. In European Conference on Computer Vision, pages 228–244. Springer, 2022.
- R. Reed. Pruning algorithms-a survey. IEEE Transactions on Neural Networks, 1993.
- Pyramidbox: A context-assisted single shot face detector. In Proceedings of the European conference on computer vision (ECCV), pages 797–813, 2018.
- Joint face detection and facial expression recognition with MTCNN. In 2017 4th International Conference on Information Science and Control Engineering (ICISCE), pages 424–427, 2017.
- WIDER FACE: A face detection benchmark. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5525–5533, 2016.
- EXTD: Extremely tiny face detector via iterative filter reuse. arXiv preprint arXiv:1906.06579, 2019.
- Faceboxes: A CPU real-time face detector with high accuracy. In 2017 IEEE International Joint Conference on Biometrics (IJCB), pages 1–9. IEEE, 2017.
- S3FD: Single shot scale-invariant face detector. In Proceedings of the IEEE international conference on computer vision, pages 192–201, 2017.
- Real-time multi-scale face detector on embedded devices. Sensors, 2019.
- Deep-learning steganalysis for removing document images on the basis of Geometric Median pruning. Symmetry, 2020.
- Tinaface: Strong but simple baseline for face detection. arXiv preprint arXiv:2011.13183, 2020.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.