LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language (“cross-madal”) decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders, concurrent to the Transformer's overwhelming success in many other vision-language tasks. Adopting a different…

• SA
  Shanghai Association for Science and Technology

  Award: 20DZ1100800
• EA
  Engineering and Physical Sciences Research Council

  Award: EP/N019474/1