Research map / Detection and segmentation / Open-set and few-shot detection
Visual-Geometric Collaborative Guidance for Affordance Learning
Hongchen Luo, Wei Zhai, Jiao Wang, Yang Cao, Zheng-Jun Zha
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 text guidance (ablation) | VCR-Net · CAL Seen | KLD: 0.613 -> 0.595 | Improved |
| add text guidance (ablation) | VCR-Net · CAL Obj Unseen | KLD: 1.259 -> 1.056 | Improved |
| add text guidance (ablation) | VCR-Net · CAL Aff Unseen | KLD: 1.641 -> 1.489 | Improved |
| add pose guidance (ablation) | VCR-Net · CAL Seen | KLD: 0.664 -> 0.595 | Improved |
| add pose guidance (ablation) | VCR-Net · CAL Obj Unseen | KLD: 1.219 -> 1.056 | Improved |
| add pose guidance (ablation) | VCR-Net · CAL Aff Unseen | KLD: 1.635 -> 1.489 | Improved |
| add apparent similarity transfer (ablation) | VCR-Net · CAL Seen | KLD: 0.708 -> 0.595 | Improved |
| add apparent similarity transfer (ablation) | VCR-Net · CAL Obj Unseen | KLD: 1.252 -> 1.056 | Improved |
| add apparent similarity transfer (ablation) | VCR-Net · CAL Aff Unseen | KLD: 1.624 -> 1.489 | Improved |
| add apparent similarity transfer (ablation) | VCR-Net · CAL Seen | SIM: 0.665 -> 0.692 | Improved |
| add text guidance (ablation) | VCR-Net · CAL Aff Unseen | SIM: 0.365 -> 0.382 | Improved |
| replace PIANet with VCR-Net | affordance learning model · CAL Obj Unseen | KLD: 1.194 -> 1.056 | 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 3 of 3 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
- Leverage Interactive Affinity for Affordance Learning (CVPR 2023 · similarity 0.96)
- Learning Affordance Grounding From Exocentric Images (CVPR 2022 · similarity 0.91)
- Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models (CVPR 2026 · similarity 0.90)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.90)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.89)
- Weakly Supervised Multimodal Affordance Grounding for Egocentric Images (AAAI 2024 · similarity 0.89)
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.
