Argus-Lite detection: COCO val2017 mAP 0.273 / AP@50 0.496 / AR@100 0.432

README.md

@@ -58,7 +58,7 @@ All four heads trained on pre-cached ViT-S features produced by a single forward
 | Classifier | ImageNet-1k train | 224 px CLS token | SGD, lr 30, WD 0, cosine, 30 epochs | 82.87 % train top-1 / **79.13 % val top-1 / 95.53 % val top-5** |
 | Segmentation | ADE20K (20,210 train / 2,000 val) | 512 px, 32×32 grid | AdamW, lr 1e-3, 5 epochs | mIoU 0.417 |
 | Depth | NYUv2 (32K train / 5K val) | 416 px, 26×26 grid, 256-bin | SILog, AdamW, lr 1e-4, 3 epochs | RMSE 0.715 |
-| Detection | COCO train 2017 (117 K) | 768 px, 48×48 grid | FCOS targets, AdamW, lr 1e-4, 2 epochs | loss cls 0.25 / reg 0.33 / ctr 0.60; RF100-VL AR@100 0.266 (20-domain subset) |
+| Detection | COCO train 2017 (117 K) | 768 px, 48×48 grid | FCOS targets, AdamW, lr 1e-4, 2 epochs | **COCO val2017 mAP 27.3** (AP@50 49.6 · AR@100 43.2); RF100-VL AR@100 0.266 (20-domain subset) |
 
 Training logs per head live alongside the weights (`*_training_log.json`).
 
@@ -90,7 +90,7 @@ Per-domain numbers live in `rf100vl_results.json`.
 ## Evaluation details
 
 - Classifier val top-1 is **79.13 %**, top-5 **95.53 %** on 50K ImageNet val 2012 images, using the TensorFlow Models repo's synset-label mapping for ground truth. Above the EUPE-ViT-S paper kNN baseline (78.2).
-- Detection head ships training-loss curves and the RF100-VL cross-domain AR@100 number above; COCO val2017 mAP is a future addition.
+- Detection head: COCO val2017 mAP 0.273 (AP@50 0.496, AP@75 0.268, AR@100 0.432). See `coco_val_eval.json` for the full breakdown including per-size AP.
 - Depth head here is a BN + two-conv + 256-bin variant. A full DPT decoder reassembling the four hooked block activations from the cache is the natural next iteration.
 - Segmentation head is a linear probe at 5 epochs; the EUPE-ViT-S paper reports mIoU 0.466 at a much longer schedule.
 

coco_val_eval.json

@@ -0,0 +1,16 @@
+{
+  "AP_0.5_0.95": 0.27296165044742066,
+  "AP_0.5": 0.49611133070799174,
+  "AP_0.75": 0.2683562201186404,
+  "AP_small": 0.1348535251743501,
+  "AP_medium": 0.2942910951580116,
+  "AP_large": 0.3935789222521886,
+  "AR_maxDets_1": 0.2496661617343009,
+  "AR_maxDets_10": 0.40529583390755014,
+  "AR_maxDets_100": 0.43203417814208595,
+  "AR_small": 0.24303236448644558,
+  "AR_medium": 0.4745727259450976,
+  "AR_large": 0.5823425288609941,
+  "n_images": 5000,
+  "n_predictions": 291404
+}