Remove projections (1024 native), add satellite text, dual GatedFusion

Architecture changes:
- Removed proj_drone/proj_sat (1024→512): retrieval space is now
  DINOv3 native 1024-dim, no information loss from projection
- TextFusionMLP: 2304→1024→1024 (was 2304→768→512), shared between branches
- Gallery branch now uses satellite captions (L1/L2/L3) via shared TextFusionMLP
- Two separate GatedFusion gates: α_q (query) and α_g (gallery)
- For sat images without captions (~57%): gate passes image features through

Dataset changes:
- GTAUAVDataset now loads satellite captions from caption index
- collate_gtauav_batch includes sat_caption_l1/l2/l3

Training loop:
- Passes satellite captions to model forward
- Logs both gate_q and gate_g values

11.1M trainable / 734M total (1.51%)

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

src/training/train_gtauav.py

@@ -61,7 +61,6 @@ class TrainConfigGTAUAV:
     dino_web_path: str = _DINO_WEB
     dino_sat_path: str = _DINO_SAT
     lrsclip_path: str = _LRSCLIP
-    proj_dim: int = 512
     init_gate: float = 0.7
     baseline_mode: bool = False
 
@@ -169,6 +168,9 @@ def _evaluate(
                 caption_l1=batch["caption_l1"],
                 caption_l2=batch["caption_l2"],
                 caption_l3=batch["caption_l3"],
+                sat_caption_l1=batch["sat_caption_l1"],
+                sat_caption_l2=batch["sat_caption_l2"],
+                sat_caption_l3=batch["sat_caption_l3"],
             )
         all_query.append(embeddings["query"].cpu())
         all_gallery.append(embeddings["gallery"].cpu())
@@ -193,7 +195,8 @@ def _evaluate(
         hit = (top_k == targets.unsqueeze(1)).any(dim=1).float()
         metrics[f"r@{k}_g2q"] = float(hit.mean().item())
 
-    metrics["gate"] = model.fusion.gate_value
+    metrics["gate_q"] = model.fusion_query.gate_value
+    metrics["gate_g"] = model.fusion_gallery.gate_value
     return metrics
 
 
@@ -233,7 +236,6 @@ def train(cfg: TrainConfigGTAUAV) -> None:
             dino_web_path=cfg.dino_web_path,
             dino_sat_path=cfg.dino_sat_path,
             lrsclip_path=cfg.lrsclip_path,
-            proj_dim=cfg.proj_dim,
             init_gate=cfg.init_gate,
             baseline_mode=cfg.baseline_mode,
             device=cfg.device,
@@ -372,6 +374,9 @@ def train(cfg: TrainConfigGTAUAV) -> None:
                         caption_l1=batch["caption_l1"],
                         caption_l2=batch["caption_l2"],
                         caption_l3=batch["caption_l3"],
+                        sat_caption_l1=batch["sat_caption_l1"],
+                        sat_caption_l2=batch["sat_caption_l2"],
+                        sat_caption_l3=batch["sat_caption_l3"],
                     )
             # Loss in fp32 (learnable temperature gradient overflows in fp16).
             loss_dict = loss_fn(
@@ -402,19 +407,21 @@ def train(cfg: TrainConfigGTAUAV) -> None:
             pbar.set_postfix(
                 loss=f"{total_loss.item():.3f}",
                 tau=f"{loss_dict['temperature'].item():.4f}",
-                gate=f"{loss_dict['gate'].item():.3f}",
+                gq=f"{loss_dict['gate_q'].item():.3f}",
+                gg=f"{loss_dict['gate_g'].item():.3f}",
             )
 
         elapsed = time.time() - epoch_start
 
         means = {k: v / max(n_batches, 1) for k, v in agg.items()}
         LOGGER.info(
-            "📈 epoch=%d  time=%.1fs  lr=%.2e  loss=%.4f  tau=%.4f  gate=%.4f",
+            "📈 epoch=%d  time=%.1fs  lr=%.2e  loss=%.4f  tau=%.4f  gate_q=%.4f  gate_g=%.4f",
             epoch, elapsed,
             optimizer.param_groups[0]["lr"],
             means.get("total", 0.0),
             means.get("temperature", 0.0),
-            means.get("gate", 1.0),
+            means.get("gate_q", 1.0),
+            means.get("gate_g", 1.0),
         )
 
         epoch_record: dict = {
@@ -428,12 +435,13 @@ def train(cfg: TrainConfigGTAUAV) -> None:
             val_metrics = _evaluate(model, test_loader, cfg.device)
             epoch_record["val"] = val_metrics
             LOGGER.info(
-                "🎯 val epoch=%d  R@1=%.4f  R@5=%.4f  R@10=%.4f  gate=%.4f",
+                "🎯 val epoch=%d  R@1=%.4f  R@5=%.4f  R@10=%.4f  gate_q=%.4f  gate_g=%.4f",
                 epoch,
                 val_metrics.get("r@1_q2g", 0.0),
                 val_metrics.get("r@5_q2g", 0.0),
                 val_metrics.get("r@10_q2g", 0.0),
-                val_metrics.get("gate", 1.0),
+                val_metrics.get("gate_q", 1.0),
+                val_metrics.get("gate_g", 1.0),
             )
 
         history.append(epoch_record)
@@ -469,11 +477,12 @@ def train(cfg: TrainConfigGTAUAV) -> None:
 
     LOGGER.info("✅ Training complete. Report: %s", report_path)
     LOGGER.info(
-        "📊 Final — R@1=%.4f  R@5=%.4f  R@10=%.4f  gate=%.4f",
+        "📊 Final — R@1=%.4f  R@5=%.4f  R@10=%.4f  gate_q=%.4f  gate_g=%.4f",
         final_metrics.get("r@1_q2g", 0.0),
         final_metrics.get("r@5_q2g", 0.0),
         final_metrics.get("r@10_q2g", 0.0),
-        final_metrics.get("gate", 1.0),
+        final_metrics.get("gate_q", 1.0),
+        final_metrics.get("gate_g", 1.0),
     )