AI Paper Atlas

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

Learning Attribute–Affordance Hierarchies in Hyperbolic Space for Open-Vocabulary 3D Object Affordance Grounding

Yuxuan Wang, Tong Li, Yihang Zhu, Guangtao Lyu, Yukuan Min, Chenghao Xu, Jiexi Yan, Xu Yang, Cheng Deng

ICML 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception

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 contrastive loss L_cont (ablation)AAH · PIADv2 SeenAUC: 92.00 -> 93.29Improved
add contrastive loss L_cont (ablation)AAH · PIADv2 Unseen ObjectAUC: 79.65 -> 81.01Improved
add ordering loss L_ord (ablation)AAH · PIADv2 Unseen AffordanceAUC: 70.10 -> 70.90Improved
add counterfactual exclusion loss L_cf (ablation)AAH · PIADv2 Unseen AffordanceAUC: 70.30 -> 70.90Improved
add counterfactual exclusion loss L_cf (ablation)AAH · PIADv2 SeenAUC: 92.75 -> 93.29Improved
add hypergraph construction (ablation)AAH · PIADv2 Unseen ObjectAUC: 80.71 -> 81.01Improved
use hyperbolic space instead of Euclidean mean pooling (ablation)AAH · PIADv2 Unseen ObjectAUC: 79.85 -> 81.01Improved
use hyperbolic space instead of Euclidean concat+linear (ablation)AAH · PIADv2 Unseen AffordanceAUC: 70.25 -> 70.90Improved
use hyperbolic geometry instead of Euclidean with same hierarchical supervision (ablation)AAH · PIADv2 Unseen AffordanceAUC: 70.25 -> 70.90Improved
use hierarchical losses instead of standard segmentation loss in hyperbolic space (ablation)AAH · PIADv2 Unseen ObjectAUC: 80.32 -> 81.01Improved
add contrastive loss to GREAT (ablation)GREAT · PIADv2 Unseen ObjectAUC: 79.57 -> 79.99Improved
raise hypergraph distance threshold from 3 to 4 or 5 (ablation)AAH · PIADv2AUCHurt

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