Research map / Detection and segmentation / Open-set and few-shot detection
Multi-label Affordance Mapping from Egocentric Vision
Lorenzo Mur-Labadia, Jose J. Guerrero, Ruben Martinez-Cantin
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 |
|---|---|---|---|
| replace multi-class softmax with independent binary classifiers trained with Asymmetric loss (ablation) | DeepLab-v3 · easy-EPIC Aff test | mIoU (%): 19.5 -> 42.3 | Improved |
| replace multi-class softmax with independent binary classifiers trained with Asymmetric loss (ablation) | FPN · easy-EPIC Aff test | mIoU (%): 12.9 -> 39.8 | Improved |
| use Asymmetric loss instead of plain BCE (ablation) | DeepLab-v3 · easy-EPIC Aff test | mIoU (%): 31.3 -> 42.3 | Improved |
| use Asymmetric loss instead of plain BCE (ablation) | FPN · easy-EPIC Aff test | mIoU (%): 22.2 -> 39.8 | Improved |
| use Asymmetric loss instead of plain BCE (ablation) | U-Net · easy-EPIC Aff test | mIoU (%): 20.9 -> 17.7 | Hurt |
| use dynamic threshold instead of top-K selection for multi-class heuristics (ablation) | multi-class segmentation models · easy-EPIC Aff test | mIoU (%): 8.9 -> 12.9 (FPN) | Improved |
| increase number of winning classes in top-K heuristic (ablation) | multi-class segmentation models · easy-EPIC Aff test | mIoU | Hurt |
| use DeepLab-v3 decoder instead of FPN or U-Net (ablation) | Asym multi-label segmentation · easy-EPIC Aff test | mIoU (%): 17.7 (U-Net) / 39.8 (FPN) -> 42.3 | Improved |
| use Mask R-CNN instead of best multi-label segmentation model | detection metrics · easy-EPIC Aff test | mAP (%): Mask-RCNN 59.3 mAP, 62.6 AP50 | Improved |
| increase affordance classes from 20 to 43 (ablation) | DeepLab-v3 Asym · EPIC-Aff | mIoU (%): 42.3 -> 31.1 | Hurt |
Closest papers by meaning
- Weakly Supervised Multimodal Affordance Grounding for Egocentric Images (AAAI 2024 · similarity 0.90)
- Learning Precise Affordances from Egocentric Videos for Robotic Manipulation (ICCV 2025 · similarity 0.90)
- Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors (ICLR 2025 · similarity 0.89)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.87)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds (ICLR 2025 · similarity 0.87)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (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.
