Research map / Detection and segmentation / Open-set and few-shot detection
Leverage Interactive Affinity for Affordance Learning
Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, Dacheng Tao
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 |
|---|---|---|---|
| Use interactive-affinity learning with IFE and KHP | Affordance learning · CAL Seen | KLD: 1.198 -> 0.965 | Improved |
| Use interactive-affinity learning with IFE and KHP | Affordance learning · CAL Unseen | KLD: 3.016 -> 2.823 | Improved |
| Add IFE and KHP rather than using neither (ablation) | Pose-aided interactive affinity learning · CAL Seen | KLD: 1.208 -> 0.965 | Improved |
| Add IFE and KHP rather than using neither (ablation) | Pose-aided interactive affinity learning · CAL Unseen | KLD: 5.593 -> 2.823 | Improved |
| Add KHP to IFE (ablation) | Pose-aided interactive affinity learning · CAL Seen | KLD: 1.126 -> 0.965 | Improved |
| Add KHP to IFE (ablation) | Pose-aided interactive affinity learning · CAL Unseen | KLD: 4.558 -> 2.823 | Improved |
| Add IFE to KHP (ablation) | Pose-aided interactive affinity learning · CAL Seen | KLD: 1.164 -> 0.965 | Improved |
| Add IFE to KHP (ablation) | Pose-aided interactive affinity learning · CAL Unseen | KLD: 3.576 -> 2.823 | Improved |
| Use separate body-part keypoint features instead of GAP pose features (ablation) | KHP scheme · CAL Seen | KLD: 1.317 -> 1.169 | Improved |
| Use separate body-part keypoint features instead of GAP pose features (ablation) | KHP scheme · CAL Unseen | KLD: 4.053 -> 3.933 | Improved |
| Use cross-transformer fusion instead of convolutional fusion with separate part features (ablation) | KHP scheme · CAL Seen | KLD: 1.169 -> 0.965 | Improved |
| Use cross-transformer fusion instead of convolutional fusion with separate part features (ablation) | KHP scheme · CAL Unseen | KLD: 3.933 -> 2.823 | Improved |
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.
- SegFormer — SegFormer: A Topic Segmentation Model with Controllable Range of Attention (AAAI 2023) · better on 5 of 5 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
- Visual-Geometric Collaborative Guidance for Affordance Learning (IJCV 2026 · similarity 0.96)
- Learning Affordance Grounding From Exocentric Images (CVPR 2022 · similarity 0.91)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.89)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.88)
- Weakly Supervised Multimodal Affordance Grounding for Egocentric Images (AAAI 2024 · similarity 0.88)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.87)
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.
