Lightweight Face Recognition: An Improved MobileFaceNet Model (2311.15326v1)
Abstract: This paper presents an extensive exploration and comparative analysis of lightweight face recognition (FR) models, specifically focusing on MobileFaceNet and its modified variant, MMobileFaceNet. The need for efficient FR models on devices with limited computational resources has led to the development of models with reduced memory footprints and computational demands without sacrificing accuracy. Our research delves into the impact of dataset selection, model architecture, and optimization algorithms on the performance of FR models. We highlight our participation in the EFaR-2023 competition, where our models showcased exceptional performance, particularly in categories restricted by the number of parameters. By employing a subset of the Webface42M dataset and integrating sharpness-aware minimization (SAM) optimization, we achieved significant improvements in accuracy across various benchmarks, including those that test for cross-pose, cross-age, and cross-ethnicity performance. The results underscore the efficacy of our approach in crafting models that are not only computationally efficient but also maintain high accuracy in diverse conditions.
- An efficient face recognition method using cnn. In 2021 International Conference of Women in Data Science at Taif University (WiDSTaif), pages 1–5. IEEE, 2021.
- Mixfacenets: Extremely efficient face recognition networks. In 2021 IEEE International Joint Conference on Biometrics (IJCB), pages 1–8. IEEE, 2021.
- Irl-net: Inpainted region localization network via spatial attention. IEEE Access, 2023.
- Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4690–4699, 2019.
- Mobiface: A lightweight deep learning face recognition on mobile devices. In 2019 IEEE 10th international conference on biometrics theory, applications and systems (BTAS), pages 1–6. IEEE, 2019.
- Software defect prediction based on deep learning models: Performance study. arXiv preprint arXiv:2004.02589, 2020.
- E2f-net: Eyes-to-face inpainting via stylegan latent space. Available at SSRN 4578828, a.
- Synthetic face generation through eyes-to-face inpainting. IEEE International Joint Conference on Biometrics (IJCB 2023), b.
- A novel end-to-end deep learning scheme for classifying multi-class motor imagery electroencephalography signals. Expert Systems, 36(6):e12494, 2019.
- E2f-gan: Eyes-to-face inpainting via edge-aware coarse-to-fine gans. IEEE Access, 10:32406–32417, 2022a.
- Differential privacy preservation in robust continual learning. IEEE Access, 10:24273–24287, 2022b.
- The impact of linkability on privacy leakage. 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2023.
- Efar 2023: Efficient face recognition competition. arXiv preprint arXiv:2308.04168, 2023.
- Classification of pulmonary images by using generative adversarial networks. In 2020 8th Iranian Joint Congress on Fuzzy and intelligent Systems (CFIS), pages 133–137. IEEE, 2020.
- Airface: Lightweight and efficient model for face recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pages 0–0, 2019.
- G. Menghani. Efficient deep learning: A survey on making deep learning models smaller, faster, and better. ACM Computing Surveys, 55(12):1–37, 2023.
- Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups. arXiv preprint arXiv:2309.08442, 2023.
- Vargfacenet: An efficient variable group convolutional neural network for lightweight face recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pages 0–0, 2019.
- Face recognition: A literature survey. ACM computing surveys (CSUR), 35(4):399–458, 2003.