hypertower/v4/figures/output/md_importance_phase5.csv at 280060db82c5a8218e0a07b7556c942bd0f355d7

Files

T

rpotter6298 280060db82 Add new regression and ensemble experiment configurations for V2-M and OrthoBridge

- Introduced multiple regression experiment configurations targeting vf_md, including:
  - cd_solo_reg_set.json: CD tower only regression setup.
  - img_solo_reg_set.json: Image tower only regression setup.
  - reg_head_epoch_sweep.json: Baseline regression sweeps at different epochs (50, 75, 100).
  - reg_head_set.json: Various regression setups including baseline and OrthoBridge configurations.
  - single_eye_reg.json: Single-eye regression setup for worst-eye aggregation analysis.

- Added ensemble configurations for OrthoBridge with different inner bridges:
  - ortho_alts_ensemble.json: Ensemble tests with ConcatBridge, PairwiseAdditiveBridge, and GatedAdditiveBridge.
  - ortho_alts_tritower.json: Tritower tests with the same inner bridges.

- Created V2-M specific configurations:
  - baseline_reg_nt50.json: Regression baseline with V2-M backbone.
  - geom_vec_gt.json and geom_vec_unet.json: Geometry vector injection experiments with V2-M.
  - single_l1_bridges.json: Single-eye ensemble experiments with various bridge types.
  - tritower_geom_gt.json: Tritower setup with GT contour-rasterized masks.

- Promoted existing experiments to higher repetitions for robustness.

2026-06-11 15:08:20 +02:00

516 B

Raw Blame History

1	feature	mean_importance	std_importance
2	Age	0.03184101084778838	0.017362350323790826
3	IOP_corr	0.0209298093602393	0.01619384191432414
4	Gender	0.010245143460808846	0.020271910566046904
5	Phakic/Pseudophakic	0.005718439848904106	0.019878985551523384
6	eyeID	0.002907359675067821	0.0068517202428395665
7	Pachymetry	0.0027483776870354105	0.008864856763204554
8	dioptre_2	8.49432781653429e-05	0.0010216320594945336
9	astigmatism	-0.0012830897957007016	0.0044473592790778
10	dioptre_1	-0.002925119731183013	0.006220349074293031

516 B Raw Blame History

516 B

Raw Blame History