artifacts/vg_5k/region_oracle.json


1
2
3
4
5
6
7
8
9
10

{
  "protocol": "DIAGNOSTIC, NOT A METHOD. Each annotated region box is encoded as a crop and paired with its own description, so the two modalities carry the same parts in the same order. That box-to-phrase link is cross-modal supervision a deployed system would not have.",
  "scenes": 256,
  "mean_parts": 15.95703125,
  "correlation": 0.6646459453410474,
  "anchor_bound_with_part_oracle": 0.359375,
  "anchor_bound_unsupervised_reference": 0.336,
  "within_modality_ceiling_text": 0.805,
  "reading": "A large jump means part correspondence is the whole problem and is an engineering target. Staying near 0.336 means the two encoders do not covary at the part level either, and no aggregation rescues this corpus."
}