AI Paper Atlas

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

Closed-Loop Transfer for Weakly-supervised Affordance Grounding

Jiajin Tang, Zhengxuan Wei, Ge Zheng, Sibei Yang

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 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 shared CAM (ablation)one-way baseline · AGD20K-SeenKLD: 1.318 -> 1.259Improved
add shared CAM (ablation)one-way baseline · AGD20K-UnseenKLD: 1.635 -> 1.508Improved
add denoising distillation (ablation)one-way baseline · AGD20K-SeenKLD: 1.318 -> 1.251Improved
add denoising distillation (ablation)one-way baseline · AGD20K-UnseenKLD: 1.635 -> 1.468Improved
add pixel alignment on top of shared CAM (ablation)shared CAM · AGD20K-SeenKLD: 1.259 -> 1.149Improved
add pixel alignment on top of shared CAM (ablation)shared CAM · AGD20K-UnseenKLD: 1.508 -> 1.335Improved
add denoising distillation on top of shared CAM plus pixel alignment (ablation)LoopTrans · AGD20K-SeenKLD: 1.149 -> 1.088Improved
add pixel alignment on top of shared CAM plus denoising distillation (ablation)LoopTrans · AGD20K-UnseenKLD: 1.431 -> 1.247Improved
raise exo:ego ratio from 3:1 to 4:1 (ablation)LoopTrans · AGD20K-SeenKLD: 1.088 -> 1.068Improved
raise exo:ego ratio from 3:1 to 4:1 (ablation)LoopTrans · AGD20K-UnseenKLD: 1.247 -> 1.285Hurt
add noise-absorbing heads (0 to 15) (ablation)LoopTrans · AGD20KKLDImproved
use MSE plus Dice loss instead of either alone for pixel decoder (ablation)LoopTrans · AGD20K-UnseenKLDImproved

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