Quaternion-Valued Correlation Learning for Few-Shot Semantic Segmentation
IEEE Transactions on Circuits and Systems for Video Technology
Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to represent novel classes. The correlation-based methods lack the ability to consider interaction of the two subspace matching scores due to the inherent nature of the real-valued 2D convolutions. In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra. Specifically, our QCLNet is formulated as a hyper-complex valued network and represents correlation tensors in the quaternion domain, which uses quaternion-valued convolution to explore the external relations of query subspace when considering the hidden relationship of the support sub-dimension in the quaternion space. Extensive experiments on the PASCAL- 5i and COCO- 20i datasets demonstrate that our method outperforms the existing state-of-the-art methods effectively.
Guangzhou Science and Technology Program key projects
correlation learning, Few-shot learning, quaternion-valued convolution, semantic segmentation
Industrial and Systems Engineering
Zewen Zheng, Guoheng Huang, Xiaochen Yuan, Chi Man Pun, Hongrui Liu, and Wing Kuen Ling. "Quaternion-Valued Correlation Learning for Few-Shot Semantic Segmentation" IEEE Transactions on Circuits and Systems for Video Technology (2023): 2102-2115. https://doi.org/10.1109/TCSVT.2022.3223150