Pikaliov
2ce4017ebd
Self-contained experimental track validating generated text captions
via retrieval R@1 lift on UAV-VisLoc.
Architecture: GeoRSCLIP ViT-B/32 dual encoder, 512-dim shared space.
Loss: 4-term InfoNCE (img-img + sat-cap + drone-cap + cap-cap)
with cosine temperature decay, PALW-like curriculum.
Metric: delta R@1 (with text - without text) >= +3% => PASS.
Gin-configured (balanced / baseline_no_text / text_heavy variants).
Follows NADEZHDA code style.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
12 lines
334 B
Plaintext
12 lines
334 B
Plaintext
# Baseline: image-image only, no captions. Reference R@1 for delta computation.
|
|
# L = 1.0 * L_img_img
|
|
|
|
include 'balanced.gin'
|
|
|
|
# Disable all caption loss terms.
|
|
MultiTermInfoNCE.lambda_sc_max = 0.0
|
|
MultiTermInfoNCE.lambda_dc_max = 0.0
|
|
MultiTermInfoNCE.lambda_cc_max = 0.0
|
|
|
|
TrainConfig.output_dir = "out/caption_test/baseline_no_text"
|