Research map / Vision-language and multimodal / Robot action and navigation
FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation
Xinyu Sun, Peihao Chen, Jugang Fan, Jian Chen, Thomas H. Li, Mingkui Tan
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 |
|---|---|---|---|
| Condition observation features on fine-grained goal features with FiLM layers | FGPrompt-MF · MP3D cross-domain | SR: 14.6% -> 77.6% | Improved |
| Replace late fusion with channel concatenation and joint modeling (ablation) | ImageNav navigation policy · Gibson ImageNav | SR: 13.0% -> 78.9% | Improved |
| Add keypoint-matching fusion to late fusion (ablation) | ImageNav navigation policy · Gibson ImageNav | SR: 13.0% -> 41.6% | Improved |
| Preserve spatial resolution rather than average-pooling goal activations for FiLM mapping (ablation) | FGPrompt-MF · Gibson ImageNav | SR: 32.0% -> 77.3% | Improved |
| Fuse at early ResNet blocks instead of increasing fusion depth to 4 blocks (ablation) | FGPrompt-MF · Gibson ImageNav | SR: 71.4% -> 77.3% | Improved |
| Concatenate goal and observation images along channels instead of stacking them for 3D convolution (ablation) | FGPrompt-EF · Gibson ImageNav | SR: 20.5% -> 78.9% | Improved |
| Jointly model goal and observation images rather than share encoder parameters (ablation) | FGPrompt-EF · Gibson ImageNav | SR: 14.6% -> 78.9% | Improved |
| Use mid fusion rather than no fusion under randomly varied goal-camera parameters (ablation) | ImageNav navigation policy · Augmented camera-parameter ImageNav | SR: 12.1% -> 70.2% | Improved |
| Use mid fusion rather than early fusion (ablation) | ImageNav navigation policy · Augmented camera-parameter ImageNav | SR: 64.6% -> 70.2% | Improved |
| Use mid fusion rather than early fusion (ablation) | ImageNav navigation policy · Instance image navigation | SR: 3.4% -> 9.9% | Improved |
| Add early fusion between the unshuffled image and current observation | ResNet18+IL rearrangement baseline · AI2THOR 1-Phase Rearrangement | Success: 1.89 -> 10.2 (+439%) | Improved |
Closest papers by meaning
- GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance (NeurIPS 2024 · similarity 0.86)
- REGNav: Room Expert Guided Image-Goal Navigation (AAAI 2025 · similarity 0.85)
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.85)
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs (ICML 2024 · similarity 0.85)
- Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation (NeurIPS 2025 · similarity 0.85)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · 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.
