Multi-Similarity Enhancement Network for Few-Shot Segmentation

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, this study extracts and fuses multiple support-query similarity, and keep enhancing them with convolutional operations. Experimental results reveal that our approach achieves a performance of 66.8% in PASCAL and 43.8% in COCO, surpassing the state-of-the-art (SOTA) and outperforming other leading competitors.

Keywords

• Few-shot semantic
• few-shot learning
• semantic segmentation