6ad9c4d149
V3 architecture for CVGL caption validation on GTA-UAV-LR dataset: - AsymmetricEncoder: DINOv3 ViT-L/16 (LVD drone + SAT satellite, frozen) + LRSCLIP/DGTRS-CLIP ViT-L-14 text encoder (248 tok, partial unfreeze) - L1/L2/L3 hierarchical captions from VLM-generated descriptions - TextFusionMLP (concat 3x768 -> MLP -> 512) + GatedFusion - Segmentation filter: exclude images with >=90% background+water - 10.9M trainable / 733M total params, 256x256 input - coloredlogs + tqdm + emoji for training UX - Baseline mode (--baseline): image-only, no text encoder loaded Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
8 lines
178 B
Python
8 lines
178 B
Python
"""Loss functions for caption quality test."""
|
|
from src.losses.multi_infonce import (
|
|
InfoNCELoss,
|
|
cosine_temperature,
|
|
)
|
|
|
|
__all__ = ["InfoNCELoss", "cosine_temperature"]
|