AI Paper Atlas

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

INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding

Ji Ha Jang, Hoigi Seo, Se Young Chun

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 10 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 interaction relationship-guided contrastive loss (ablation)supervised contrastive baseline · AGD20K SeenmKLD: 1.678 -> 1.439Improved
add object-variance mitigation loss on top of L_inter (ablation)INTRA · AGD20K SeenmKLD: 1.439 -> 1.199Improved
use LLM-generated relationship map instead of WordNet (ablation)INTRA · AGD20K SeenmKLD: 1.701 -> 1.439Improved
use LLM relationship map instead of Word2Vec or GloVe co-occurrence (ablation)INTRA · AGD20K SeenmKLD: 1.547 / 1.519 -> 1.439Improved
add text synonym augmentation (ablation)INTRA · AGD20K UnseenmKLD: 1.563 -> 1.365Improved
add text synonym augmentation for novel verb 'take photo' (ablation)INTRA · AGD20K novel verb 'take photo'mKLD: 0.922 -> 0.648Improved
use ALBEF text encoder instead of BERT (ablation)INTRA · AGD20K UnseenmKLD: 1.458 -> 1.365Improved
use ALBEF text encoder instead of random embedding (ablation)INTRA · AGD20K SeenmKLD: 1.230 -> 1.199Mixed
use 3 projection layers instead of 1 (ablation)INTRA · AGD20K SeenmKLD: 1.380 -> 1.199Improved
train with exocentric images only versus LOCATE with paired imagesINTRA · AGD20K SeenmKLD: 1.226 -> 1.199Improved

Later papers that compared with this method

1 later accepted paper reports INTRA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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