[3N1-GS-7] Vision, speech media processing:

[3N1-GS-7-01] A Zero-Shot Segmentation Method Considering Boundary Quality with Weighted Residual Connections

〇Haruki Nagami¹, Kosuke Sakurai¹, Ayako Yamagiwa¹, Masayuki Goto¹ (1. Waseda university)

Keywords:Zero-Shot Segmentation, RobustSAM, Degraded Image, Boundary Quality, Residual Connections

Zero-shot segmentation is an image segmentation task that also detects unlearned objects. Segement Anything Model (SAM), that is a representative zero-shot segmentation model is capable of outputting highly accurate pixel masks of unlearned objects indicated by prompts, such as points, that are specified as objects of interest. RobustSAM is a method that adapts SAM to degraded images by incorporating a mechanism to remove noise in SAM. On the other hand, the quality near the boundary of a clear image is lower than that of a SAM, because the degradation information removal mechanism removes the boundary information at the same time. Therefore, this study proposes a novel segmentation model that can flexibly consider embeddings before removing degraded information by adding a residual connection mechanism using a weighted average to RobustSAM. Our proposed method enables us to improve the boundary quality of clear images. Furthermore, through experiments on real data, we show that the proposed method improves the accuracy for clear images while maintaining the accuracy for degraded images.