Pyramid Co-Attention Compare Network for Few-Shot Segmentation
Defu Zhang, Ronghua Luo, Xuebin Chen and 1 more
IEEE Access · 2021
doi:10.1109/access.2021.3118472 (opens in a new tab)
We email you when a new notice or a question about this paper appears.
Abstract
Few-shot segmentation (FSS), which aims to extract never learned classes of objects from <italic>query</italic> images with a few annotated <italic>support</italic> samples, is a challenging problem especially in the cases that the appearance of objects in the <italic>support</italic> and the <italic>query</italic> images is significant different. Therefore, we propose a deep network called Pyramid Co-Attention Compare Network (PCCNet) to narrow the gap between them by introducing a Pyramid Co-attention Module (PCAM). PCAM acts as a task-specific transformer to transform the features of corresponding objects in <italic>query</italic> and <italic>support</italic> images into a space in which they are much closer by taking advantage of the underlying relation between <italic>query</italic> and <italic>support</italic> images. We also introduce a Prototypical Guide Module (PGM) which uses non-parametric metric learning to guide parametric metric learning so as to combine the advantages of them. In addition, a Superpixel Refine Module(SRM) is proposed to optimize the final output segmentation masks. Experiments conducted on Pascal-<inline-formula> <tex-math notation="LaTeX">$5^{i}$ </tex-math></inline-formula> shows that our PCCNet achieves a mean Intersection-over-Union(mIoU) score of 63.01% for 1-shot segmentation and 64.57% for 5-shot segmentation, outperforming state-of-the-art methods by margin of 2.2% and 1.6%, respectively.
Abstract licence: CC BY-NC-ND
Reads
Read by people on this page
None yet.
Checked or read by AI through naulon
None yet.
A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.
Are you an author?
Is this your paper?
Claim it to add your note and be paid when agents cite it. Free.