SwiftVLN for SatNav — Random History Sampling
Related Repositories
- SwiftVLN: training and evaluation code for these checkpoints.
- SatNav: satellite-image navigation environments, datasets, and evaluation tools.
This checkpoint is designed for SwiftVLN on SatNav, the continuous-state vision-and-language navigation benchmark over satellite imagery. It studies random sampling of earlier observations for long-term visual memory.
Model
- Starting checkpoint:
Qwen/Qwen2.5-VL-3B-Instruct - Training data: SatNav-v0.1 offline expert trajectories
- Training: 1 epoch, full-parameter fine-tuning, learning rate
2e-5 - Context: 32 RGB frames, up to 8 randomly sampled history frames
- Prediction horizon: 4 actions
- Memory: per-frame average pooling with stride 2
Repository name
swiftvln-satnav: SwiftVLN trained and evaluated on SatNav3b: Qwen2.5-VL 3B backbone1ep: trained for one epochf32s4: uses a 32-frame window and predicts four actionsoverlap0: uses non-overlapping training windowspf-h8-random: randomly samples up to eight history framespool-s2: applies average pooling with stride 2noembed: uses no embedding enhancement
Reference Results
Results reported in the SatNav paper, memory-design ablation, row Random sampling.
SR, SPL, and OS are percentages. Changes in SR and OS are percentage points relative to the SwiftVLN reference model.
| Split | SR (%) | SPL (%) | OS (%) | Delta SR (pp) | Delta OS (pp) |
|---|---|---|---|---|---|
Test Seen (val_seen) | 52.0 | 51.6 | 67.9 | -13.8 | -4.5 |
Test Unseen (val_unseen) | 41.1 | 40.9 | 57.6 | -12.6 | -6.5 |
Usage
Use this checkpoint with the SwiftVLN evaluation guide. Keep the full repository name unchanged because SwiftVLN derives the evaluation configuration from it.
This checkpoint is a history-sampling ablation in the SwiftVLN SatNav Ablation Model Zoo.