AI Paper Atlas

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

Weakly-Supervised Learning of Dense Functional Correspondences

Stefan Stojanov, Linan Zhao, Yunzhi Zhang, Daniel L. K. Yamins, Jiajun Wu

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 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 spatial contrastive loss to functional-only training (ablation)Ours · Real evaluation datasetPCK@23p: 0.336 -> 0.516Improved
add functional contrastive loss to spatial-only training (ablation)Ours · Real evaluation datasetAP@23p: 0.382 -> 0.691Improved
add mask loss (ablation)Ours · Real evaluation datasetBest F1@23p: 0.775 -> 0.808Improved
add mask loss (ablation)Ours · Real evaluation datasetPCK@23p: 0.516 -> 0.501Hurt
add CogVLM grounding to DINODINO · Real evaluation datasetAP@23p: 0.382 -> 0.561Improved
prompt ManipVQA with function instead of part name (ablation)ManipVQA + DINO · Real evaluation datasetPCK@23p: 0.398 -> 0.309Hurt
distill into learned features instead of off-the-shelf DINODINO · Real evaluation datasetNormalized Dist: 0.206 -> 0.153Improved
use LoRA finetuning and FiLM text conditioning (ablation)Ours · Synthetic/Real evaluationNormalized Dist: 0.172 to 0.181No clear effect
increase backbone from ViT-S to ViT-G (ablation)Ours (with mask loss) · Real evaluation datasetPCK@23p: 0.494 -> 0.523Improved
increase spatial loss weight from 1 to 10 (ablation)Ours · Real evaluation datasetPCK@23p: 0.443 -> 0.501Improved
increase mask loss weight from 1 to 10 (ablation)Ours · Real evaluation datasetAP@23p: 0.730 -> 0.719No clear effect
add half stride to ViT-B backbone (ablation)Ours (with mask loss) · Real evaluation datasetAP@10p: 0.360 -> 0.403Improved

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