From bd6f3b8d3368c6459d07df383bb0f1df734d8df0 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Sat, 1 Aug 2026 23:48:26 -0500 Subject: Visual Genome is capped: part correspondence buys 0.023 Each VG region box is index-aligned with its own description, so the crop can be encoded and paired with the phrase describing it -- part correspondence by annotation, which is cross-modal supervision a deployed system would not have. The cross-modal anchor bound goes 0.336 -> 0.359. So the two encoders do not covary at the part level either, and no segmentation, aggregation, kernel or backbone repairs that. The 0.805 within-text ceiling was never the cross-modal ceiling; for this encoder pair on this corpus the cross-modal ceiling is about 0.36 against the 0.9 recovery needs. Six representational interventions this session were chosen without a ceiling in view -- the same error being made on the matching side at the same time. What replaces them is a three-number screening protocol that runs before any pipeline is built. Co-Authored-By: Claude --- artifacts/vg_5k/region_oracle.json | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 artifacts/vg_5k/region_oracle.json (limited to 'artifacts/vg_5k/region_oracle.json') diff --git a/artifacts/vg_5k/region_oracle.json b/artifacts/vg_5k/region_oracle.json new file mode 100644 index 0000000..969266a --- /dev/null +++ b/artifacts/vg_5k/region_oracle.json @@ -0,0 +1,10 @@ +{ + "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." +} \ No newline at end of file -- cgit v1.2.3