Utilizing Complex-valued Network for Learning to Compare Image Patches
This work addresses the under-explored area of complex-valued networks for image similarity tasks, offering a novel method for researchers in computer vision.
The authors tackled the problem of learning image descriptors for patch comparison by proposing a complex-valued network approach, achieving competitive results on benchmark datasets.
At present, the great achievements of convolutional neural network(CNN) in feature and metric learning have attracted many researchers. However, the vast majority of deep network architectures have been used to represent based on real values. The research of complex-valued networks is seldom concerned due to the absence of effective models and suitable distance of complex-valued vector. Motived by recent works, complex vectors have been shown to have a richer representational capacity and efficient complex blocks have been reported, we propose a new approach for learning image descriptors with complex numbers to compare image patches. We also propose a new architecture to learn image similarity function directly based on complex-valued network. We show that our models can perform competitive results on benchmark datasets. We make the source code of our models publicly available.