Abstract

Face verification in unconstrained environments remains a challenging task due to significant variations in illumination, pose, expression, and occlusion, which can degrade the stability of learned representations. Although deep metric learning approaches have demonstrated strong performance on large-scale datasets, their effectiveness often diminishes in data-constrained or heterogeneous scenarios, where global feature embeddings may capture non-discriminative or noise-sensitive patterns. To address this limitation, this paper introduces the Hybrid Invariant–Siamese Attention Network (HISANet), a lightweight Siamese architecture augmented with a channel attention mechanism based on the Squeeze-and-Excitation principle. The proposed model adaptively recalibrates channel-wise feature responses, enabling the network to emphasize identity-relevant information while suppressing less informative variations. A shared convolutional backbone is used to generate compact embeddings, and similarity between image pairs is computed using scaled cosine similarity within a binary classification framework. The network is trained end-to-end using a binary cross-entropy objective and evaluated on the Labeled Faces in the Wild (LFW) dataset following the standard verification protocol. A comprehensive evaluation, including accuracy, area under the ROC curve, equal error rate, and qualitative analysis, demonstrates that the integration of channel attention improves feature selectivity and reduces overfitting. HISANet achieves a validation accuracy of 75.83% and an equal error rate of 20.13%, indicating that attention-based feature recalibration can enhance robustness while maintaining computational efficiency.

References

• M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
• D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vis., vol. 60, no. 2, pp. 91-110, 2004.
• H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” in Proc. ECCV, 2006, pp. 404-417.
• Y. Taigman et al., “DeepFace: Closing the gap to human-level performance in face verification,” in Proc. CVPR, 2014.
• F. Schroff et al., “FaceNet: A unified embedding for face recognition and clustering,” in Proc. CVPR, 2015.
• W. Liu et al., “SphereFace: Deep hypersphere embedding for face recognition,” in Proc. CVPR, 2017.
• H. Wang et al., “CosFace: Large margin cosine loss for deep face recognition,” in Proc. CVPR, 2018.
• J. Deng et al., “ArcFace: Additive angular margin loss for deep face recognition,” in Proc. CVPR, 2019.
• Y. Huang et al., “CurricularFace: Adaptive curriculum learning loss for deep face recognition,” in Proc. CVPR, 2020.
• Q. Meng et al., “MagFace: A universal representation for face recognition,” in Proc. CVPR, 2021.
• M. Kim et al., “AdaFace: Quality adaptive margin for face recognition,” in Proc. CVPR, 2022.
• Y. Boutros et al., “ElasticFace: Elastic margin loss for face recognition,” in Proc. CVPR, 2022.
• J. Hu et al., “Squeeze-and-Excitation Networks,” in Proc. CVPR, 2018.
• S. Woo et al., “CBAM: Convolutional Block Attention Module,” in Proc. ECCV, 2018.
• H. Wang et al., “Vision Transformers for Face Recognition,” IEEE TPAMI, 2023.
• J. Bromley et al., “Signature verification using a Siamese time delay neural network,” 1993.
• R. Hadsell et al., “Dimensionality reduction by learning an invariant mapping,” in Proc. CVPR, 2006.
• S. Chen et al., “MobileFaceNets: Efficient CNNs for real-time face verification,” arXiv:1804.07573, 2018.
• X. Wu et al., “A light CNN for deep face representation,” IEEE TIFS, 2018.