Research map / Detection and segmentation / Open-set and few-shot detection
Generative Meta-Adversarial Network for Unseen Object Navigation
Sixian Zhang, Weijie Li, Xinhang Song, Yubing Bai, Shuqiang Jiang
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 feature generator (FG) (ablation) | A3C · AI2THOR unseen objects | SR (%): 21.50 -> 23.20 | Improved |
| add environmental meta discriminator (EMD) to FG (ablation) | A3C · AI2THOR unseen objects | SR (%): 23.20 -> 28.03 | Improved |
| add PS module (ablation) | A3C · AI2THOR unseen objects | SR (%): 21.50 -> 32.70 | Improved |
| add FG (ablation) | A3C† · AI2THOR unseen objects | SR (%): 32.70 -> 34.20 | Improved |
| add EMD to PS+FG (ablation) | A3C† · AI2THOR unseen objects | SR (%): 34.20 -> 48.83 | Improved |
| add meta-learning to EMD (ablation) | GMAN† · AI2THOR unseen objects | SR (%): 41.93 -> 48.83 | Improved |
| use learned discriminator instead of cosine similarity (ablation) | GMAN† · AI2THOR unseen objects | SR (%): 46.47 -> 48.83 | Improved |
| add distance reward to navigation reward (ablation) | A3C · AI2THOR unseen objects | SR (%): 14.50 -> 18.43 | Improved |
| add similarity reward to navigation reward (ablation) | A3C · AI2THOR unseen objects | SR (%): 14.50 -> 21.43 | Improved |
| use mixed reward Rn+d+s instead of Rn (ablation) | A3C · AI2THOR unseen objects | SR (%): 14.50 -> 21.50 | Improved |
| add GMAN to A3C | A3C · AI2THOR seen objects | SR (%): 31.37 -> 39.30 | Improved |
| add GMAN† over EOTP† | EOTP† · RoboTHOR unseen objects | SR (%): 21.53 -> 27.67 | Improved |
Closest papers by meaning
- Learning on the Go: A Meta-learning Object Navigation Model (ICCV 2025 · similarity 0.88)
- VTNet: Visual Transformer Network for Object Goal Navigation (ICLR 2021 · similarity 0.87)
- Auxiliary Tasks and Exploration Enable ObjectGoal Navigation (ICCV 2021 · similarity 0.87)
- Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding (CVPR 2023 · similarity 0.87)
- Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR 2024 · similarity 0.86)
- Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation (NeurIPS 2025 · similarity 0.85)
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.
