Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation
Xiaobo Yang, Xiaojin Gong
Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results.…
cs.CV2024
Tuning-free Universally-Supervised Semantic Segmentation
Xiaobo Yang, Xiaojin Gong
This work presents a tuning-free semantic segmentation framework based on classifying SAM masks by CLIP, which is universally applicable to various types of supervision. Initially,…