FireViewer DINOv3 pointing pilot v1
Quick card
| Field | Reference |
|---|---|
| Use | Inspect the retained five-epoch multi-task research pilot. |
| Expected input | 448×448 RGB; segmentation, point heatmap, abstention and presence heads. |
| Example | Use the matching loader to inspect presence and spatial outputs; retain abstentions. |
| Limits | Not a production model; point PCK uses only nine positive validation rows. Public visibility does not resolve retained release restrictions. |
| Contract | Model contract · Safe weight loading |
Choose a variant · Resource navigation · Update log
Research archive, currently publicly visible on the Hub, of a five-epoch DINOv3 ViT-B/16 multi-task pilot for visible fire/smoke presence, segmentation, point localization and explicit visual abstention.
This repository preserves a completed, reloadable experiment. It is not a production model and not independently benchmarked. The retained release records describe a private pilot policy; current public visibility does not resolve that restriction or establish redistribution permission. The word “pilot” is part of the model identity and should not be removed in downstream documentation.
Model contract
- Base model:
facebook/dinov3-vitb16-pretrain-lvd1689m - Immutable base revision:
5931719e67bbdb9737e363e781fb0c67687896bc - Architecture:
DinoV3MultiTaskModel, schema 4 - Input size: 448 × 448 RGB
- Heads: segmentation, point heatmap, visual abstention, fire/smoke presence
- Presence labels:
flame_visible,smoke_visible - Training: full-model fine-tuning, five epochs, 8,192 balanced samples/epoch
- Selection: minimum validation loss, epoch 5
Validation record
The metrics below come from the campaign validation split. They are not an independent benchmark and must not be compared directly with the frozen object detection benchmark used for YOLO, D-FINE and RT-DETR.
| Metric | Epoch 5 result | Evidence boundary |
|---|---|---|
| Validation loss | 0.02892 | 11,007 validation rows |
| Segmentation IoU | 0.86718 | Aggregate is strongly influenced by negative/background rows |
| Segmentation Dice | 0.92887 | Same boundary as IoU |
| Point PCK@10 | 0.55556 | Only 9 positive point rows |
| Point-negative specificity | 0.99402 | 6,188 negative point rows |
| Presence exact-match accuracy | 0.91778 | 11,007 presence rows |
| Flame-presence F1 | 0.87507 | Validation split only |
| Smoke-presence F1 | 0.93582 | Validation split only |
The training split contains 36,039 rows but only 134 rows in the positive
pointing role. This imbalance and the nine positive validation points make the
localization score too uncertain for a scientific or operational claim. See
validation-summary.json and the machine reports in
reports/.
Artifacts
model.safetensors: preferred inference weights; 271 tensors and 94,127,621 parameter values were converted and byte-for-byte tensor checked.checkpoints/best.pt: native epoch-5 selected checkpoint.checkpoints/last.pt: full optimizer/scheduler resume checkpoint at epoch 5.dinov3_adapter.py: exact FireViewer schema-4 architecture used for loading.config.json: pinned architecture, base revision and artifact paths.artifact-manifest.json: release inventory and recorded checkpoint identity.
Loading the safe weights
Access to the gated DINOv3 base configuration and acceptance of Meta's DINOv3 terms are required. The published safetensors file contains the full trained backbone and all FireViewer heads; the base repository is used to instantiate the pinned architecture configuration.
from dinov3_adapter import DinoV3MultiTaskModel
model = DinoV3MultiTaskModel.from_safetensors(
"model.safetensors",
model_id="facebook/dinov3-vitb16-pretrain-lvd1689m",
revision="5931719e67bbdb9737e363e781fb0c67687896bc",
image_size=448,
token=True,
)
network = model.network.eval()
The caller remains responsible for applying the same image normalization and for interpreting logits from each head. Do not treat a heatmap maximum as a verified geographic coordinate.
Rights, limitations and safety
The derived weights remain subject to the DINOv3 terms and to applicable
source-specific obligations documented by the training receipts. Public or private
access does not grant redistribution rights. See
RIGHTS_AND_ATTRIBUTION.md.
This model is not a certified warning system. It must not be used alone to confirm a fire, trigger an alert, order an evacuation or direct emergency response.
Visibility and retained release policy
The unauthenticated Hub API confirms this repository is public on 5 October 2026. The retained artifact-manifest.json and validation-summary.json still describe its historical private pilot/release policy. Those evidence files are preserved. This card corrects the description of observed visibility; it does not approve a public release, change repository access, clear source rights or promote the pilot. The retained private release policy is not superseded by this documentation update.
Sensitive outputs require human review. A heatmap point is an image-space proposal, not a verified base in the terrain or a hidden ignition origin. The nine positive validation points cannot support a robust localization claim. No independent positive-point benchmark or new evaluation is supplied by this documentation update.
Retrieve the matching loader and weights
from huggingface_hub import hf_hub_download
weights = hf_hub_download(
repo_id="fireviewer/dinov3-pointing-pilot-v1",
revision="bd4cc7e15e296fa95b1cd9478f6952a21a4201ec",
filename="model.safetensors",
)
Retrieve dinov3_adapter.py, config.json and the matching requirements from
the same revision before using the loading example above. That example assumes
the loader is importable and the weights are at the stated local path.
Documentation and revision
Card updated in English on 5 October 2026, from the public repository at
bd4cc7e15e296fa95b1cd9478f6952a21a4201ec and its retained reports.
This update checks documentation, repository metadata and small evidence files;
it does not rerun training, inference, dataset payload verification or device qualification.
Historical receipts keep their original dates, revisions and scope. Earlier README
hashes in artifact manifests refer to those earlier releases.
The association FIRE-VIEWER provides administrative and financial stewardship for resources under its control. Technical governance is maintainer-led. Upstream, source-specific and pre-association rights remain separate; repository placement does not transfer ownership or grant additional rights.
Project documentation · Institutional website. Contact: contact@fire-viewer.fr.
Likes are always welcome! ❤️ If these resources help you, a little heart makes our day and helps others discover the work. Thank you!