AI Paper Atlas

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

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

WonJun Moon, Hyun Seok Seong, Jae-Pil Heo

ICCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 3 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 object-level prototypical contrastive learning (ablation)classification baseline · AGD20K-SeenKLD: 1.349 -> 1.271Improved
add object-level pixel contrastive learning (ablation)object-level proto model · AGD20K-SeenKLD: 1.271 -> 1.219Improved
add part-level prototypical contrastive learning (ablation)object-level proto + pixel model · AGD20K-SeenKLD: 1.219 -> 1.164Improved
add part-level pixel contrastive learning (ablation)object+part proto, object pixel · AGD20K-SeenKLD: 1.157 -> 1.142Improved
add CAM calibration with object affinity map (ablation)full contrastive model · AGD20K-SeenKLD: 1.142 -> 1.124Improved
add CAM calibration with object affinity map (ablation)classification baseline · AGD20K-SeenKLD: 1.349 -> 1.271Improved
add object-level pixel contrastive learning on top of object+part proto (ablation)object+part proto model · AGD20K-SeenSIM: 0.416 -> 0.414No clear effect
replace CLIP with ClearCLIP (ablation)DINO+CLIP model · AGD20K-SeenKLD: 1.160 -> 1.124Improved
use prompt 'an item to {action} with' instead of bare action (ablation)zero-shot ClearCLIP · AGD20K-SeenKLD: 1.672 -> 1.574Improved
use CLIP affinity map instead of DINO attention for pIoU (ablation)full model · AGD20K-UnseenKLD: 1.243 -> 1.257Hurt
use CLIP affinity map instead of DINO attention for pIoU (ablation)full model · AGD20K-SeenKLD: 1.124 -> 1.126No clear effect
selective contrastive learning vs LOCATELOCATE · AGD20K-UnseenKLD: 1.405 -> 1.243Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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