Skip to main content
Search

# Region-Localized Preference Optimization

1 related articles

Subscribe to updates
  1. arXiv

    KAIST team turns prompt-template disagreement into preference supervision, lifting open-vocabulary segmentation across the MESS benchmark without pixel-level labels

    The work proposes a preference-guided adaptation framework for open-vocabulary semantic segmentation that converts the segmentation differences different prompt templates produce on the same image (prompt disagreement) into binary preference supervision, adapting models with Region-Localized Preference Optimization (RLPO) plus consistency regularization in a streaming single-step setting, achieving consistent gains on the five domain groups of the MESS benchmark across SAN and CAT-Seg backbones (ViT-B/16 and ViT-L/14) without any pixel-level annotation and remaining effective under noisy preferences.

You’re all caught up