AI RESEARCH
TALENT: Target-aware Efficient Tuning for Referring Image Segmentation
arXiv CS.CV
•
ArXi:2604.00609v1 Announce Type: new Referring image segmentation aims to segment specific targets based on a natural text expression. Recently, parameter-efficient tuning (PET) has emerged as a promising paradigm. However, existing PET-based methods often suffer from the fact that visual features can't emphasize the text-referred target instance but activate co-category yet unrelated objects. We analyze and quantify this problem, terming it the `non-target activation' (NTA) issue.