Answers are grounded in this paper and cite their sources.
Few-shot segmentation (FSS) methods aim to segment objects of novel classes with relatively few annotated samples. Prototype learning, a popular approach in FSS, employs prototype vectors to transfer information from known classes (support images) to novel classes(query images) for segmentation. However, using only prototype vectors may not be sufficient to represent all features of the support image. To extract abundant features and make more precise predictions, we propose a Multi-Similarity and Attention Network (MSANet) including two novel modules, a multi-similarity module and an attention module. The multi-similarity module exploits multiple feature-map of support images and query images to estimate accurate semantic relationships. The attention module instructs the MSANet to concentrate on class-relevant information. We evaluated the proposed network on standard FSS datasets, PASCAL-<tex-math notation="LaTeX">5ⁱ</tex-math> 1-shot, PASCAL-<tex-math notation="LaTeX">5ⁱ</tex-math> 5-shot, COCO-<tex-math notation="LaTeX">20ⁱ</tex-math> 1-shot, and COCO-<tex-math notation="LaTeX">20ⁱ</tex-math> 5-shot. An MSANet model with a ResNet101 backbone achieved state-of-the-art performance for all four benchmark datasets with mean intersection over union (mIoU) values of 69.13%, 73.99%, 51.09%, and 56.80%, respectively. The code used is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/AIVResearch/MSANet</uri>.
No takes yet. Share an insight, caveat, or question.
Iqbal et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: