Plain-language protocol text in the fine-tuned profile manifest
Browse files
results/tuned_deployment_evaluation.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"method": "AnomalyDINO-inspired DINOv2 ViT-S/14 fine-tuned on synthetic defects; 32,768-patch coreset memory",
|
| 3 |
"profile": "dinov2_tuned_v1",
|
| 4 |
-
"protocol": "Official VisA test assignments.
|
| 5 |
"encoder_sha256": "95ac11984ecae1bb14e9a0d98e85650e73365fc3d57ed49c6bfa526e0498adcb",
|
| 6 |
"device": "cuda",
|
| 7 |
"categories": {
|
|
|
|
| 1 |
{
|
| 2 |
"method": "AnomalyDINO-inspired DINOv2 ViT-S/14 fine-tuned on synthetic defects; 32,768-patch coreset memory",
|
| 3 |
"profile": "dinov2_tuned_v1",
|
| 4 |
+
"protocol": "Official VisA test assignments. The DINOv2 encoder was fine-tuned on synthetic defects made from normal training images (last 4 blocks only). The memory bank is a 32,768-patch coreset of normal-image patches per product. Thresholds are the 95th percentile of held-out normal scores (80th for Macaroni 1 and 2); held-out normals are never used to build the memory. Retrospective development evaluation on test images that were seen during development; not an untouched external test.",
|
| 5 |
"encoder_sha256": "95ac11984ecae1bb14e9a0d98e85650e73365fc3d57ed49c6bfa526e0498adcb",
|
| 6 |
"device": "cuda",
|
| 7 |
"categories": {
|