AI Paper Atlas

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

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos Tolias

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic 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
add class relevance weights w_c (ablation)RnS · Avg mIoU 6 benchmarks, B=1mIoU: 41.20 -> 41.59Improved
add class relevance weights w_c (ablation)RnS · Avg mIoU 6 benchmarks, B=10mIoU: 48.54 -> 49.02Improved
use multiple mixing coefficients Lambda instead of single 0.8 (ablation)RnS · Avg mIoU 6 benchmarks, B=1mIoU: 36.40 -> 41.20Improved
use multiple mixing coefficients Lambda instead of single 0.8 (ablation)RnS · Avg mIoU 6 benchmarks, B=10mIoU: 48.38 -> 48.54Improved
add textual support (class names) (ablation)RnS · Avg mIoU 6 benchmarks, B=1mIoU: 34.11 -> 41.59Improved
add textual support (class names) (ablation)RnS · Avg mIoU 6 benchmarks, B=10mIoU: 48.00 -> 49.02Improved
use K=4 neighbours instead of K=1 in kNN retrieval (ablation)RnS · Avg mIoU 6 benchmarks, B=1mIoU: 40.02 -> 41.59Improved
increase K from 4 to 32 (ablation)RnS · Avg mIoU 6 benchmarks, B=5mIoU: 47.87 -> 47.59No clear effect
add pseudo-label loss for classes without visual support (ablation)RnS · partial visual supportmIoUImproved
retrieve nearest support features instead of random subset of support set (ablation)RnS · retrieval analysismIoUImproved
use RnS on top of zero-shot DINOv3.txt + SAM at B=20DINOv3.txt + SAM · OVS vs fully supervised avgmIoU: 27.9 -> 61.9Improved
add visual support (partial, 90% classes unseen)RnS · VOC all-class mIoUmIoU: 52.85 -> 52.04No clear effect

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