MARIS: Referring Image Segmentation via Mutual-Aware Attention Features

arXiv:2311.15727v2 Announce Type: replace
Abstract: Referring image segmentation (RIS) aims to segment a particular region based on a language expression prompt. Existing methods incorporate linguistic features into visual features and obtain multi-modal features for mask decoding. However, these methods may segment the visually salient entity instead of the correct referring region, as the multi-modal features are dominated by the abundant visual context. In this paper, we propose MARIS, a referring image segmentation method that leverages the Segment Anything Model (SAM) …

abstract arxiv attention cs.cv decoding features however image language modal multi-modal prompt segment segmentation type via visual