AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MARCO: Navigating the Unseen Space of Semantic Correspondence

Claudia Cuttano, Gabriele Trivigno, Carlo Masone, Stefan Roth

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 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 adapters to frozen DINOv2 (ablation)MARCO architecture · SPair-71kPCK@0.10: 53.9 -> 76.9Improved
add the upsampling head after adapters (ablation)MARCO architecture · SPair-71kPCK@0.10: 76.9 -> 87.2Improved
use coarse-to-fine sigma schedule instead of fixed sigma=3 (ablation)MARCO supervision · SPair-71kPCK@0.01: 19.5 -> 27.0Improved
use coarse-to-fine sigma schedule instead of fixed sigma=1 (ablation)MARCO supervision · SPair-71kPCK@0.10: 81.0 -> 87.2Improved
add dense self-distillation loss (ablation)MARCO · SPair-UPCK@0.10: 41.8 -> 67.5Improved
use raw semantic flow as pseudo-labels in dense loss (ablation)MARCO dense self-distillation · SPair-UPCK@0.10: 41.8 -> 49.6Mixed
add Delaunay triangulation and piecewise-affine warp to MNN matches (ablation)MARCO dense self-distillation · SPair-UPCK@0.10: 52.5 -> 64.7Improved
add GT keypoint anchoring of flow clusters (ablation)MARCO dense self-distillation · SPair-UPCK@0.10: 64.7 -> 67.5Improved
fully fine-tune the DINOv2 backbone instead of keeping it frozen (ablation)DINOv2 · SPair-UPCK@0.10: 54.9 -> 43.9Hurt
use AdaptFormer instead of LoRA (ablation)MARCO adaptation · SPair-UPCK@0.10: 65.6 -> 67.5Improved
add flow-anchoring self-distillation loss to Geo-SCGeo-SC · SPair-UPCK@0.10: 56.9 -> 63.4Improved
use coarse-to-fine loss instead of InfoNCE + l2 (ablation)Adapter + Upsample model · SPair-71kPCK@0.01: 20.0 -> 26.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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