PaperScope
LIVE · 2026-09-17 05:40 UTC

SetPlanner: A Lightweight Plug-in Point-Set Planner for Frozen SAM

Dawei Yan, Yuezhe Yang, Menglan Ruan, Chunfeng Yang, Yudong Zhang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.18037 v1
Category
Submitted
2026-09-16

Abstract

Segment Anything Models provide reusable priors, yet they require user prompts and cannot support fully automatic instrument segmentation. Automatic prompting is difficult for thin, articulated, reflective, and partly occluded tools, where several configurations can be valid. We formulate automatic prompting as lightweight point-set planning and isolate the point source under a frozen pathway. To this end, we present SetPlanner, a 1.52M-parameter plug-in point-set planner for frozen SAM. The plug-in preserves SAM's point-prompt interface and enables reuse across backbones. SetPlanner plans complete unordered K-point sets from geometry-aware targets with a permutation-aware conditional flow. SAM decodes eight candidates; their consensus readout yields a ground-truth-free prediction. Across three endoscopic datasets, SetPlanner wins all six transfer routes over a LoRA-adapted system. Under our frozen-pathway protocol, SetPlanner reaches 0.934 Dice on Kvasir-Instrument and recovers 96% of a 44.4-point localization gap, while candidate disagreement ranks low-Dice cases at AUROC 0.969.

Comment: 5 pages, 2 figures, 3 tables. Submitted to IEEE ICASSP 2027

arXiv abs page · PDF · same-day batch