Multi-Similarity Enhancement Network for Few-Shot Segmentation
Open Access
- 17 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 73521-73530
Abstract
Few-Shot Segmentation (FSS) is challenging for intra-class diversity and support sample scarcity. Many works focus on the class-wise or pixel-wise similarity between the support foreground and query sample while neglecting the support background, which is vital for FSS to suppress the related query background. In this paper, we propose a Multi-Similarity Enhancement Network (MSENet) to remedy this issue by extracting the pixel-wise support-query similarity of the foreground and background. To remedy the shift issue, caused by the huge difference between support and query target objects, we extract and fuse multiple support-query similarity, and keep enhancing them with convolutional operations. Experiments on three benchmarks demonstrate that our approach reaches SOTA performances and outperforms the best competitors with many desirable advantages.Keywords
Funding Information
- National Key Research and Development Program of China (2020AAA0140004)
This publication has 48 references indexed in Scilit:
- SG-One: Similarity Guidance Network for One-Shot Semantic SegmentationIEEE Transactions on Cybernetics, 2020
- FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation2020
- Meta-Seg: A Generalized Meta-Learning Framework for Multi-Class Few-Shot Semantic SegmentationIEEE Access, 2019
- PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment2019
- Panoptic Feature Pyramid Networks2019
- Feature Pyramid Networks for Object Detection2017
- Pyramid Scene Parsing Network2017
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009