Spaces:
Configuration error
Configuration error
unicorn who dev commited on
Update model catalogue and evidence boundaries
Browse files
README.md
CHANGED
|
@@ -13,28 +13,32 @@ FireViewer is an independent research and engineering project maintained by
|
|
| 13 |
|
| 14 |
| Resource | Evidence-backed status |
|
| 15 |
| --- | --- |
|
| 16 |
-
| [D-FINE-M strict v1](https://huggingface.co/fireviewer/fire-smoke-dfine-m-strict-v1) | Primary research candidate.
|
| 17 |
-
| [RT-DETRv2-R50 Fire/Smoke](https://huggingface.co/fireviewer/rtdetr-v2-r50-fire-smoke) | Conservative reference.
|
| 18 |
-
| [YOLO11-M strict v1](https://huggingface.co/fireviewer/fire-smoke-yolo11m-strict-v1) |
|
| 19 |
-
| [
|
|
|
|
| 20 |
|
| 21 |
-
The
|
| 22 |
`Hajorda/flameye-wildfire-detection@test` at immutable revision
|
| 23 |
`361a3dea8b877482af9f4ed80eff77ffd39926ef`. Its final selection has zero exact
|
| 24 |
-
overlap with FireViewer train/validation hashes.
|
| 25 |
-
|
| 26 |
|
| 27 |
## Other public resources
|
| 28 |
|
|
|
|
| 29 |
- [Prithvi Burn Scars Training Dataset v1](https://huggingface.co/datasets/fireviewer/prithvi-burnscars-training-dataset-v1)
|
| 30 |
- [DINOv3 Cross-View FireViewer v1](https://huggingface.co/datasets/fireviewer/dinov3-cross-view-fireviewer-v1-dataset)
|
| 31 |
- [FireWarning Training Bundles v1](https://huggingface.co/datasets/fireviewer/firewarning-train-bundles-v1)
|
| 32 |
- [Simple Measured Scenes v1](https://huggingface.co/datasets/fireviewer/simple-measured-scenes-v1)
|
| 33 |
- [Dataset from Simulations](https://huggingface.co/datasets/fireviewer/dataset-from-simulations)
|
| 34 |
|
| 35 |
-
Private calibration, holdout
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## Provenance, rights and integrity
|
| 40 |
|
|
@@ -45,7 +49,9 @@ before use or redistribution.
|
|
| 45 |
|
| 46 |
Metrics are comparable only when dataset, split, immutable revision,
|
| 47 |
preprocessing and evaluation protocol are identical. A model prediction is a
|
| 48 |
-
probabilistic output, not geographic truth or publication authority.
|
|
|
|
|
|
|
| 49 |
|
| 50 |
## Code and contact
|
| 51 |
|
|
@@ -53,3 +59,4 @@ probabilistic output, not geographic truth or publication authority.
|
|
| 53 |
- [Canonical documentation](https://github.com/fireviewer/Fireviewer_doc)
|
| 54 |
- [Unicorn Who Dev](https://unicornwhodev.com)
|
| 55 |
- Rights, collaboration and removal requests: unicornwhodev@gmail.com
|
|
|
|
|
|
| 13 |
|
| 14 |
| Resource | Evidence-backed status |
|
| 15 |
| --- | --- |
|
| 16 |
+
| [D-FINE-M strict v1](https://huggingface.co/fireviewer/fire-smoke-dfine-m-strict-v1) | Primary research candidate. Frozen independent COCO mAP50-95 0.3924; calibrated holdout F1 0.6475. Human review remains mandatory. |
|
| 17 |
+
| [RT-DETRv2-R50 Fire/Smoke](https://huggingface.co/fireviewer/rtdetr-v2-r50-fire-smoke) | Conservative historical reference. Frozen independent COCO mAP50-95 0.3502; lower false-alarm operating point. |
|
| 18 |
+
| [YOLO11-M strict v1](https://huggingface.co/fireviewer/fire-smoke-yolo11m-strict-v1) | Reproducible baseline, not the primary detector. Frozen independent COCO mAP50-95 0.1491; weak flame AP and recall are documented. |
|
| 19 |
+
| [RF-DETR Medium 1.10 strict v1](https://huggingface.co/fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1) | Serious validation candidate (EMA mAP50-95 0.4683 at epoch 18), but **not yet evaluated on the frozen independent benchmark**. It must not be ranked against the rows above yet. |
|
| 20 |
+
| [Strict-clean detection corpus v1](https://huggingface.co/datasets/fireviewer/fire-smoke-detection-corpus-v1) | 102,257 automatically validated rows with source-specific provenance and a 60,981 / 19,209 / 22,067 train / validation / test split. |
|
| 21 |
|
| 22 |
+
The frozen independent detector benchmark uses 512 images from
|
| 23 |
`Hajorda/flameye-wildfire-detection@test` at immutable revision
|
| 24 |
`361a3dea8b877482af9f4ed80eff77ffd39926ef`. Its final selection has zero exact
|
| 25 |
+
overlap with FireViewer train/validation hashes. Only models whose cards report
|
| 26 |
+
that exact protocol may be compared using those independent scores.
|
| 27 |
|
| 28 |
## Other public resources
|
| 29 |
|
| 30 |
+
- [SegFormer B2 fire/smoke baseline v1](https://huggingface.co/fireviewer/segformer-b2-fire-smoke-baseline-v1)
|
| 31 |
- [Prithvi Burn Scars Training Dataset v1](https://huggingface.co/datasets/fireviewer/prithvi-burnscars-training-dataset-v1)
|
| 32 |
- [DINOv3 Cross-View FireViewer v1](https://huggingface.co/datasets/fireviewer/dinov3-cross-view-fireviewer-v1-dataset)
|
| 33 |
- [FireWarning Training Bundles v1](https://huggingface.co/datasets/fireviewer/firewarning-train-bundles-v1)
|
| 34 |
- [Simple Measured Scenes v1](https://huggingface.co/datasets/fireviewer/simple-measured-scenes-v1)
|
| 35 |
- [Dataset from Simulations](https://huggingface.co/datasets/fireviewer/dataset-from-simulations)
|
| 36 |
|
| 37 |
+
Private calibration, holdout and retired training archives are not part of the
|
| 38 |
+
public catalogue. The DINOv3 pointing artifact is retained privately as a
|
| 39 |
+
five-epoch pilot because its positive localization evidence is too sparse for
|
| 40 |
+
public or operational claims. Deprecated, incomplete and superseded detector
|
| 41 |
+
repositories were removed in the 5 September 2026 cleanup.
|
| 42 |
|
| 43 |
## Provenance, rights and integrity
|
| 44 |
|
|
|
|
| 49 |
|
| 50 |
Metrics are comparable only when dataset, split, immutable revision,
|
| 51 |
preprocessing and evaluation protocol are identical. A model prediction is a
|
| 52 |
+
probabilistic output, not geographic truth or publication authority. Public
|
| 53 |
+
visibility does not imply deployment, qualification, rights clearance or
|
| 54 |
+
active use.
|
| 55 |
|
| 56 |
## Code and contact
|
| 57 |
|
|
|
|
| 59 |
- [Canonical documentation](https://github.com/fireviewer/Fireviewer_doc)
|
| 60 |
- [Unicorn Who Dev](https://unicornwhodev.com)
|
| 61 |
- Rights, collaboration and removal requests: unicornwhodev@gmail.com
|
| 62 |
+
|