Research map / Detection and segmentation / Open-set and few-shot detection
SOON: Scenario Oriented Object Navigation With Graph-Based Exploration
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 graph-based exploration to GBE (ablation) | GBE · FAO unseen house test | SR: 11.4 -> 11.9; 0.5% higher | Helped |
| Add graph-based exploration to GBE (ablation) | GBE · FAO unseen house test | SPL: 8.7 -> 10.2; 1.5% higher | Helped |
| Add graph-based exploration to GBE (ablation) | GBE · FAO unseen house test | SFPL: 0.8 -> 1.4; 0.6% higher | Helped |
| Add vision input while retaining language input (ablation) | GBE · FAO unseen house test | SR: 1.8 -> 11.9 | Helped |
| Add language input while retaining vision input (ablation) | GBE · FAO unseen house test | SR: 9.8 -> 11.9 | Helped |
| Use vision input instead of language input alone (ablation) | GBE · FAO unseen house test | SR: 1.8 -> 9.8 | Helped |
| Use object names only rather than rewritten instructions (ablation) | GBE · FAO unseen house test | SR: 11.9 -> 7.3 | Hurt |
| Add object attributes and relationships to object names (ablation) | GBE · FAO unseen house test | SR: 7.3 -> 6.2 | Hurt |
| Add region information to object names, attributes, and relationships (ablation) | GBE · FAO unseen house test | SR: 6.2 -> 6.6 | Helped |
| Use rewritten instructions rather than the three preceding annotation levels (ablation) | GBE · FAO unseen house test | SFPL: 0.8 -> 1.4; 0.6% higher | Helped |
| Use GBE rather than AuxRN | FAO unseen house test · FAO | SR: 8.1 -> 11.9 | Helped |
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.89)
- GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance (NeurIPS 2024 · similarity 0.88)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025 · similarity 0.87)
- SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation (NeurIPS 2024 · similarity 0.87)
- UniGoal: Towards Universal Zero-shot Goal-oriented Navigation (CVPR 2025 · similarity 0.87)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 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.