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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add interaction relationship-guided contrastive loss (ablation) | supervised contrastive baseline · AGD20K Seen | mKLD: 1.678 -> 1.439 | Improved |
| add object-variance mitigation loss on top of L_inter (ablation) | INTRA · AGD20K Seen | mKLD: 1.439 -> 1.199 | Improved |
| use LLM-generated relationship map instead of WordNet (ablation) | INTRA · AGD20K Seen | mKLD: 1.701 -> 1.439 | Improved |
| use LLM relationship map instead of Word2Vec or GloVe co-occurrence (ablation) | INTRA · AGD20K Seen | mKLD: 1.547 / 1.519 -> 1.439 | Improved |
| add text synonym augmentation (ablation) | INTRA · AGD20K Unseen | mKLD: 1.563 -> 1.365 | Improved |
| add text synonym augmentation for novel verb 'take photo' (ablation) | INTRA · AGD20K novel verb 'take photo' | mKLD: 0.922 -> 0.648 | Improved |
| use ALBEF text encoder instead of BERT (ablation) | INTRA · AGD20K Unseen | mKLD: 1.458 -> 1.365 | Improved |
| use ALBEF text encoder instead of random embedding (ablation) | INTRA · AGD20K Seen | mKLD: 1.230 -> 1.199 | Mixed |
| use 3 projection layers instead of 1 (ablation) | INTRA · AGD20K Seen | mKLD: 1.380 -> 1.199 | Improved |
| train with exocentric images only versus LOCATE with paired images | INTRA · AGD20K Seen | mKLD: 1.226 -> 1.199 | Improved |
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.
- Selective Contrastive Learning for Weakly Supervised Affordance Grounding (ICCV 2025 · better on 2 of 2 shared results)
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.
- LOCATE — LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding (CVPR 2023) · better on 10 of 10 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
- Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors (ICLR 2025 · similarity 0.92)
- Weakly Supervised Multimodal Affordance Grounding for Egocentric Images (AAAI 2024 · similarity 0.92)
- Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding (CVPR 2025 · similarity 0.90)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.89)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.89)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.88)
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.
