AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

INSID3: Training-Free In-Context Segmentation with DINOv3

Claudia Cuttano, Gabriele Trivigno, Christoph Reich, Daniel Cremers, Carlo Masone, Stefan Roth

CVPR 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 1 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
use frozen DINOv3 features only (no SAM, no fine-tuning) for in-context segmentationINSID3 · One-shot ICS average (9 datasets)mIoU: 47.6 -> 55.1 vs GF-SAMImproved
swap DINOv2 for DINOv3 in SAM-based GF-SAM (ablation)GF-SAM · One-shot ICS average (9 datasets)mIoU: 47.6 -> 47.0No clear effect
add positional debiasing to GF-SAM with DINOv3 (ablation)GF-SAM (DINOv3 + SAM) · One-shot ICS average (9 datasets)mIoU: 47.0 -> 48.8Improved
add positional debiasing of DINOv3 features for cross-image matching (ablation)DINOv3 on SPair-71k · SPair-71k PCK (Base, T=0.20)PCK: 59.8 -> 66.4Improved
add positional debiasing with rank s=500 (ablation)INSID3 · COCO-20i and PASCAL-PartmIoU: +3.1 % on COCO, +2.7 % on PASCALImproved
remove too many dimensions in the debiasing subspace (large rank s) (ablation)INSID3 · COCO-20i and PASCAL-PartmIoUHurt
use finer clustering (larger tau) (ablation)INSID3 · Part vs object segmentationmIoUMixed
add agglomerative clustering instead of thresholding the similarity map (ablation)INSID3 · COCO-20imIoU: 44.2 -> 50.6 (tau=0.5, single cluster)Improved
add cluster aggregation with cross-image similarity on top of fine clustering (ablation)INSID3 · PASCAL-PartmIoU: 36.2 -> 48.5Improved
add self-similarity to cross-similarity in aggregation score (ablation)INSID3 · COCO-20imIoU: 54.6 -> 57.6Improved
add self-similarity to cross-similarity in aggregation score (ablation)INSID3 · PASCAL-PartmIoU: 48.5 -> 50.5Improved
fine-tune on COCO (SegIC) for in-domain gainsSegIC · COCO-20i vs out-of-domainmIoU: COCO-20i 76.1 vs ISIC 25.3Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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