MSConv: Multiplicative and Subtractive Convolution for Face Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910865186357248 |
|---|---|
| author | Zhou, Si Si, Yain-Whar Yuan, Xiaochen Li, Xiaofan Liu, Xiaoxiang Zhang, Xinyuan Lin, Cong Gong, Xueyuan |
| author_facet | Zhou, Si Si, Yain-Whar Yuan, Xiaochen Li, Xiaofan Liu, Xiaoxiang Zhang, Xinyuan Lin, Cong Gong, Xueyuan |
| contents | In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the ability of model to extract representative and discriminative features. In the field of face recognition, traditional feature fusion methods include feature concatenation and feature addition. Recently, various attention mechanism-based fusion strategies have emerged. However, we found that these methods primarily focus on the important features in the image, referred to as salient features in this paper, while neglecting another equally important set of features for image recognition tasks, which we term differential features. This may cause the model to overlook critical local differences when dealing with complex facial samples. Therefore, in this paper, we propose an efficient convolution module called MSConv (Multiplicative and Subtractive Convolution), designed to balance the learning of model about salient and differential features. Specifically, we employ multi-scale mixed convolution to capture both local and broader contextual information from face images, and then utilize Multiplication Operation (MO) and Subtraction Operation (SO) to extract salient and differential features, respectively. Experimental results demonstrate that by integrating both salient and differential features, MSConv outperforms models that only focus on salient features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06187 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MSConv: Multiplicative and Subtractive Convolution for Face Recognition Zhou, Si Si, Yain-Whar Yuan, Xiaochen Li, Xiaofan Liu, Xiaoxiang Zhang, Xinyuan Lin, Cong Gong, Xueyuan Computer Vision and Pattern Recognition Artificial Intelligence In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the ability of model to extract representative and discriminative features. In the field of face recognition, traditional feature fusion methods include feature concatenation and feature addition. Recently, various attention mechanism-based fusion strategies have emerged. However, we found that these methods primarily focus on the important features in the image, referred to as salient features in this paper, while neglecting another equally important set of features for image recognition tasks, which we term differential features. This may cause the model to overlook critical local differences when dealing with complex facial samples. Therefore, in this paper, we propose an efficient convolution module called MSConv (Multiplicative and Subtractive Convolution), designed to balance the learning of model about salient and differential features. Specifically, we employ multi-scale mixed convolution to capture both local and broader contextual information from face images, and then utilize Multiplication Operation (MO) and Subtraction Operation (SO) to extract salient and differential features, respectively. Experimental results demonstrate that by integrating both salient and differential features, MSConv outperforms models that only focus on salient features. |
| title | MSConv: Multiplicative and Subtractive Convolution for Face Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.06187 |