Abstract
Referring image segmentation aims to segment the entity referred by a natural language description. Previous methods tackle this problem by conducting multimodal feature interaction between image and words or sentence only. However, considering only single granularity feature interaction tends to result in incomplete understanding of visual and linguistic information. To overcome this limitation, we propose to conduct multi-granularity multimodal feature interaction by introducing a Word-Granularity Feature Modulation (WGFM) module and a Sentence-Granularity Context Extraction (SGCE) module, which can be complementary in feature alignment and obtain a comprehensive understanding of the input image and referring expression. Extensive experiments show that our method outperforms previous methods and achieves new state-of-the-art performances on four popular datasets, i.e., UNC (+1.45%), UNC+ (+1.63%), G-Ref (+0.47%) and ReferIt (+1.02%).
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
