Global–Local Query-Support Cross-Attention for Few-Shot Semantic Segmentation

Fengxi Xie, Guozhen Liang and Ying-Ren Chien ()
Additional contact information
Fengxi Xie: Department of Electrical Engineering and Computer Science, Technische Universität Berlin, 10623 Berlin, Germany
Guozhen Liang: Department of Electrical Engineering and Computer Science, Technische Universität Berlin, 10623 Berlin, Germany
Ying-Ren Chien: Department of Electrical Engineering, National Ilan University, Yilan 260007, Taiwan

Mathematics, 2024, vol. 12, issue 18, 1-14

Abstract: Few-shot semantic segmentation (FSS) models aim to segment unseen target objects in a query image with scarce annotated support samples. This challenging task requires an effective utilization of support information contained in the limited support set. However, the majority of existing FSS methods either compressed support features into several prototype vectors or constructed pixel-wise support-query correlations to guide the segmentation, which failed in effectively utilizing the support information from the global–local perspective. In this paper, we propose Global–Local Query-Support Cross-Attention (GLQSCA), where both global semantics and local details are exploited. Implemented with multi-head attention in a transformer architecture, GLQSCA treats every query pixel as a token, aggregates the segmentation label from the support mask values (weighted by the similarities with all foreground prototypes (global information)), and supports pixels (local information). Experiments show that our GLQSCA significantly surpasses state-of-the-art methods on the standard FSS benchmarks PASCAL-5 i and COCO-20 i .

Keywords: few-shot semantic segmentation; global–local query-support cross-attention; multi-head attention; transformer (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/18/2936/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/18/2936/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:18:p:2936-:d:1482547

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().