Mask Grounding for Referring Image Segmentation

arXiv:2312.12198v2 Announce Type: replace
Abstract: Referring Image Segmentation (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Despite significant progress in recent years, most state-of-the-art (SOTA) methods still suffer from considerable language-image modality gap at the pixel and word level. These methods generally 1) rely on sentence-level language features for language-image alignment and 2) lack explicit training supervision for fine-grained visual grounding. Consequently, they exhibit weak object-level correspondence between visual and language …

abstract algorithm art arxiv cs.cv form free gap image language objects pixel progress segment segmentation sota state type word