Papers › Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation
Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation
Zewen Zheng, Guoheng Huang, Xiaochen Yuan, Chi-Man Pun, Hongrui Liu, Wing-Kuen Ling
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. Our code is available at https://github.com/zwzheng98/QCLNet and our article "Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation" was published in IEEE Transactions on Circuits and Systems for Video Technology, vol. 33,no.5,pp.2102-2115,May 2023,doi: 10.1109/TCSVT.2022.3223150.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | QCLNet (ResNet-101) | Mean IoU | 43.6 | #40 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | QCLNet (ResNet-50) | Mean IoU | 42.3 | #50 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | QCLNet (ResNet-101) | Mean IoU | 51.9 | #29 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | QCLNet (ResNet-50) | Mean IoU | 50 | #39 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | QCLNet (ResNet-101) | Mean IoU | 67 | #31 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | QCLNet (ResNet-50) | Mean IoU | 64.3 | #62 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | QCLNet (VGG-16) | Mean IoU | 60.6 | #79 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | QCLNet (ResNet-101) | Mean IoU | 71.2 | #28 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | QCLNet (ResNet-50) | Mean IoU | 69.5 | #46 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | QCLNet (VGG-16) | Mean IoU | 64.2 | #76 of 96 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections