diff options
Diffstat (limited to 'RANK_RESULTS.md')
| -rw-r--r-- | RANK_RESULTS.md | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/RANK_RESULTS.md b/RANK_RESULTS.md index 2998e47..adaee21 100644 --- a/RANK_RESULTS.md +++ b/RANK_RESULTS.md @@ -85,6 +85,15 @@ side, all measured at matched width: | 6 spectral segments | 0.692 | 15 | | 16 spectral segments | 0.679 | 14 | | annotated region boxes (oracle) | 0.703 | 15 | +| DINOv2-base, 12 layers, 768-dim | 0.731 | 15 | +| DINOv2-large, 24 layers, 1024-dim | 0.709 | 15 | + +The backbone row was a pre-registered prediction rather than a hope: the width +had failed to respond to every other vision-side change, so a larger encoder +was predicted to leave it alone. **Doubling the depth and widening the +representation leaves the shared count at exactly 15** and moves the +correlation by less than the segmentation noise floor, in the wrong direction. +The prediction survives, and the row closes on a measurement. Handing the pipeline ground-truth boxes buys one direction over unsupervised segmentation and nothing over using fewer segments. This confirms from a new |