CO₃Net: Coordinate-Aware Contrastive Competitive Neural Network for Palmprint Recognition

Palmprint recognition achieves high discrimination for identity verification. Compared with handcrafted local texture descriptors, convolutional neural networks (CNNs) can spontaneously learn optimal discriminative features without any prior knowledge. To further enhance the features’ representation and discrimination, we propose a coordinate-aware contrastive competitive neural network (CO3Net) for palmprint recognition. To extract the multiscale textures, CO3Net consists of three parallel learnable Gabor filters (LGFs)-based texture extraction branches that learn the discriminative and robust ordering features. Due to the heterogeneity of palmprints, the effects of different textures on the final recognition performance are inconsistent, and dynamically focusing on the textures is beneficial to the performance improvement. Then, CO3Net introduces the attention modules to explore the spatial information, and selects more robust and discriminative textures. Specifically, coordinate attention (CA) is embedded into CO3Net to adaptively focus on the important textures from the positional information. Since it is difficult for the cross-entropy loss to build a compact intraclass and separate interclass feature space, the contrastive loss is employed to jointly optimize the network. CO3Net is validated on four public datasets, and the results demonstrate the remarkable recognition performance of the proposed CO3Net compared to the other state-of-the-art methods.