Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

INSID3: Training-Free In-Context Segmentation with DINOv3

About

In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i) fine-tuning vision foundation models (VFMs), which improves in-domain results but harms generalization, or (ii) combines multiple frozen VFMs, which preserves generalization but yields architectural complexity and fixed segmentation granularities. We revisit ICS from a minimalist perspective and ask: Can a single self-supervised backbone support both semantic matching and segmentation, without any supervision or auxiliary models? We show that scaled-up dense self-supervised features from DINOv3 exhibit strong spatial structure and semantic correspondence. We introduce INSID3, a training-free approach that segments concepts at varying granularities only from frozen DINOv3 features, given an in-context example. INSID3 achieves state-of-the-art results across one-shot semantic, part, and personalized segmentation, outperforming previous work by +7.5 % mIoU, while using 3x fewer parameters and without any mask or category-level supervision. Code is available at https://github.com/visinf/INSID3 .

Claudia Cuttano, Gabriele Trivigno, Christoph Reich, Daniel Cremers, Carlo Masone, Stefan Roth• 2026

Related benchmarks

TaskDatasetResultRank
Semantic segmentationCOCO-20i
mIoU (Mean)57.6
144
Semantic segmentationiSAID
mIoU56.9
122
Semantic segmentationLVIS 92^i
mIoU47.2
38
Semantic segmentationISIC
mIoU63.9
35
Semantic segmentationSUIM
mIoU61.7
34
Semantic segmentationChest X-ray
mIoU78.8
25
Semantic segmentationCOCO-20^i
mIoU65.1
24
Part SegmentationPASCAL-Part
mIoU50.5
22
Semantic segmentationiSAID 5i
mIoU52.1
21
Part SegmentationPACO-Part
mIoU38.7
17
Showing 10 of 15 rows

Other info

GitHub

Follow for update