AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Adapt Foundational Segmentation Models with Heterogeneous Searching Space

Li Yi, Jie Hu, Songan Zhang, Guannan Jiang

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
augment images with searched heterogeneous policy before zero-shot SAMSAM ViT-H · NJU2K 10-shotmIoU: 42.50 -> 80.69Improved
augment images with searched policy instead of fine-tuning SAMSAM ViT-H · CAMO 10-shotmIoU: 50.43 -> 64.34Improved
augment images with searched policy instead of fine-tuning SAMSAM ViT-H · Kvasir 10-shotmIoU: 65.21 -> 71.81Improved
augment images with searched policy instead of fine-tuning SAMSAM ViT-H · MTSD 10-shotmIoU: 59.51 -> 58.33Hurt
augment images with searched policy instead of fine-tuning SAMSAM ViT-H · KolektorSDD2 10-shotmIoU: 55.67 -> 55.83No clear effect
add radical learning-based methods (depth, normal) to search space (Complete-32 vs Mild-25) (ablation)policy search · CAMOmIoU: 51.14 -> 64.34Improved
add radical methods to search space (Complete-32 vs Mild-25) (ablation)policy search · NJU2KmIoU: 52.28 -> 80.69Improved
add 3 mild learning-based methods (Complete-32 vs Radical-29) (ablation)policy search · NJU2KmIoU: 79.61 -> 80.69Improved
use three-image reward instead of single-image reward (ablation)policy search · NJU2KmIoU: 47.95 -> 80.69Improved
use three-image reward instead of single-image reward (ablation)policy search · CAMOmIoU: 50.95 -> 64.34Improved
use reward over all few-shot images instead of three images (ablation)policy search · NJU2KmIoU: 80.69 -> 78.78Hurt
use reinforcement learning instead of random sampling of 1000 policies (ablation)policy search · NJU2KmIoU: 71.63 -> 80.69Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy