论文标题
视觉感知的完全复杂的深度学习模型
Fully complex-valued deep learning model for visual perception
论文作者
论文摘要
由于其丰富的表示能力，使用了复杂领域中的深度学习模型。但是，这些模型中的大多数要么仅限于复杂平面的第一个象限，要么将复杂值数据投影到真实域中，从而导致信息丢失。本文提出，完全在复杂域中运行会增加复杂值模型的整体性能。提出了一种新型的，完全复杂的学习方案，以使用新提出的复杂值损失函数和训练策略来训练完全复杂的卷积神经网络（FC-CNN）。 FC-CNN以CIFAR-10，SVHN和CIFAR-100的基准为基准，与其价值相比的对应物相比，增益为4-10％，维持模型的复杂性。随着参数较少，它可以达到与CIFAR-10和SVHN上最新的复杂值模型相当的性能。对于CIFAR-100数据集，它可以实现最先进的性能，参数少25％。与所有其他模型相比，FC-CNN显示出更好的训练效率和更快的收敛性。
Deep learning models operating in the complex domain are used due to their rich representation capacity. However, most of these models are either restricted to the first quadrant of the complex plane or project the complex-valued data into the real domain, causing a loss of information. This paper proposes that operating entirely in the complex domain increases the overall performance of complex-valued models. A novel, fully complex-valued learning scheme is proposed to train a Fully Complex-valued Convolutional Neural Network (FC-CNN) using a newly proposed complex-valued loss function and training strategy. Benchmarked on CIFAR-10, SVHN, and CIFAR-100, FC-CNN has a 4-10% gain compared to its real-valued counterpart, maintaining the model complexity. With fewer parameters, it achieves comparable performance to state-of-the-art complex-valued models on CIFAR-10 and SVHN. For the CIFAR-100 dataset, it achieves state-of-the-art performance with 25% fewer parameters. FC-CNN shows better training efficiency and much faster convergence than all the other models.
