Instance-Specific Feature Propagation for Referring Segmentation

Referring segmentation aims to generate a mask for the target instance indicated by natural language expression. There are typically two kinds of existing methods: one-stage methods that directly perform on fused vision and features; two-stage first utilize an model proposal then select one these instances via matching them with features. In this work, we propose novel framework simultaneously detects target-of-interest feature propagation generates fine-grained mask. our framework, each is represented Instance-Specific Feature (ISF), target-of-referring identified exchanging information among all ISFs using proposed Propagation Module (FPM). Our instance-aware approach learns relationship objects, which helps better locate than methods. Comparing methods, collaboratively interactively utilizes both synchronous identification segmentation. experimental tests, method outperforms previous start-of-the-art three RefCOCO series datasets.