.png){kind=icon}
Return
Instance-Specific Feature Propagation for Referring Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2022.3163578.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Referring segmentation aims to generate a segmentation mask for the target instance indicated by a natural language expression. There are typically two kinds of existing methods: one-stage methods that directly perform segmentation on the fused vision and language features; and two-stage methods that first utilize an instance segmentation model for instance proposal and then select one of these instances via matching them with language features. In this work, we propose a novel framework that simultaneously detects the target-of-interest via feature propagation and generates a fine-grained segmentation mask. In our framework, each instance is represented by an Instance-Specific Feature (ISF), and the target-of-referring is identified by exchanging information among all ISFs using our proposed Feature Propagation Module (FPM). Our instance-aware approach learns the relationship among all objects, which helps to better locate the target-of-interest than one-stage methods. Comparing to two-stage methods, our approach collaboratively and interactively utilizes both vision and language information for synchronous identification and segmentation. In the experimental tests, our method outperforms previous state-of-the-art methods on all three RefCOCO series datasets.
Keywords:
Feature extraction
Image segmentation
Fuses
Visualization
Task analysis
Linguistics
Proposals
Feature propagation
instance-specific
referring segmentation
Journal
IF:
9.7
Papers:
4.6K
Citations:
2.4W
Organization
Cited Papers
ShareSaveShareSaveShareSaveA retrospective 5-year review of rubella in South Africa prior to the introduction of a rubella-containing vaccine.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAIShareSaveShareSave
View more