Improve training: learnable temperature, per-group LR, warmup, augmentations

Loss:
- Learnable temperature (CLIP-style logit_scale) with clamp [0.01, 0.5]
- Replaces fixed cosine schedule (still available via --no-learnable-temp)
- Default tau_init=0.07

Optimizer:
- Per-group LR: projections 1e-4, text encoder 1e-5 (10x lower)
- Learnable temperature included in projection param group

Scheduler:
- Linear warmup (2 epochs default) + cosine annealing
- Per-step scheduling (not per-epoch)

Augmentations (separate drone/satellite):
- Drone: RandomResizedCrop(0.7-1.0), HFlip, Rotation(15), ColorJitter,
  RandomGrayscale(0.05), GaussianBlur
- Satellite: RandomResizedCrop(0.7-1.0), HFlip, ColorJitter, RandomGrayscale
- Eval: clean Resize+CenterCrop (no augmentation)

Dataset: supports separate drone_transform/sat_transform args

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/models/asymmetric_encoder.py

@@ -543,15 +543,58 @@ class AsymmetricEncoder(nn.Module):
 # Image preprocessing (DINOv3: 256x256, ImageNet normalization)
 # ---------------------------------------------------------------------------
 
+_IMAGENET_MEAN = [0.485, 0.456, 0.406]
+_IMAGENET_STD = [0.229, 0.224, 0.225]
+
+
 def get_dino_transform(image_size: int = 256) -> torch.nn.Module:
-    """Build image transform for DINOv3 input."""
+    """Build eval/inference image transform for DINOv3 input."""
     from torchvision import transforms
     return transforms.Compose([
         transforms.Resize(image_size, interpolation=transforms.InterpolationMode.BICUBIC),
         transforms.CenterCrop(image_size),
         transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406],
-            std=[0.229, 0.224, 0.225],
-        ),
+        transforms.Normalize(mean=_IMAGENET_MEAN, std=_IMAGENET_STD),
+    ])
+
+
+def get_drone_train_transform(image_size: int = 256) -> torch.nn.Module:
+    """Build training augmentation for drone images.
+
+    Includes: RandomResizedCrop, HFlip, rotation, color jitter,
+    grayscale, Gaussian blur.
+    """
+    from torchvision import transforms
+    return transforms.Compose([
+        transforms.RandomResizedCrop(
+            image_size, scale=(0.7, 1.0),
+            interpolation=transforms.InterpolationMode.BICUBIC,
+        ),
+        transforms.RandomHorizontalFlip(p=0.5),
+        transforms.RandomRotation(degrees=15),
+        transforms.ColorJitter(brightness=0.3, contrast=0.3, saturation=0.2, hue=0.1),
+        transforms.RandomGrayscale(p=0.05),
+        transforms.GaussianBlur(kernel_size=3, sigma=(0.1, 2.0)),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=_IMAGENET_MEAN, std=_IMAGENET_STD),
+    ])
+
+
+def get_satellite_train_transform(image_size: int = 256) -> torch.nn.Module:
+    """Build training augmentation for satellite images.
+
+    Lighter than drone: no rotation or blur (satellite is nadir/consistent).
+    Includes: RandomResizedCrop, HFlip, color jitter, grayscale.
+    """
+    from torchvision import transforms
+    return transforms.Compose([
+        transforms.RandomResizedCrop(
+            image_size, scale=(0.7, 1.0),
+            interpolation=transforms.InterpolationMode.BICUBIC,
+        ),
+        transforms.RandomHorizontalFlip(p=0.5),
+        transforms.ColorJitter(brightness=0.3, contrast=0.3, saturation=0.2, hue=0.1),
+        transforms.RandomGrayscale(p=0.05),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=_IMAGENET_MEAN, std=_IMAGENET_STD),
     ])