Add StripNet backbone option with Conv-MONA adaptation

StripNet-small (Strip-R-CNN, HVision-NKU) as alternative image encoder to
DINOv3 ViT-L/16. ~28M params (10x smaller). Output 512-dim from stage 4
projected to 1024 to keep retrieval space compatible with DINOv3 configs.

- src/models/stripnet/: self-contained backbone (model.py, conv_mona.py).
  State-dict naming follows upstream Strip-R-CNN repo (conv_spatial1/2);
  ImageNet-1K pretrained head dropped on load.
- Conv-MONA: 2D adaptation of MONA (CVPR 2025) for CNN blocks. BN → 1x1
  Down(C->bn) → multi-scale DWConv {3,5,7} mean → +residual → GELU →
  1x1 Up(bn->C) with channel-wise layer scale γ init 1e-6. Two adapters
  per StripNet Block (post-attn, post-mlp); injected into deepest N stages.
- StripNetEncoder: GAP + Linear(512->1024). Overrides train() to keep
  frozen BatchNorm stats stable across mode flips.
- AsymmetricEncoder: new `backbone="stripnet"` option (always shared).
- TrainConfigGTAUAV: backbone, stripnet_path, stripnet_mona_last_n_stages.
- conf/gtauav_balanced_stripnet.gin + gtauav_baseline_stripnet.gin.

Smoke test: forward [2,3,256,256] -> [2,1024]. Trainable: 1.2M baseline
(8.27%), 4.76M with text (3.35% of 142M).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

conf/gtauav_balanced_stripnet.gin

@@ -0,0 +1,27 @@
+# GTA-UAV Balanced (StripNet backbone): StripNet-small + Conv-MONA in last 2 stages.
+# Replaces DINOv3 ViT-L/16 with strip-shaped DWConv hierarchical CNN (~28M params,
+# 10× smaller than DINOv3). Output 512-dim → projected to 1024 to match retrieval space.
+#
+# Trainable:
+#   - Projection (Linear 512→1024): ~525K
+#   - Conv-MONA in stages 3 & 4 (2 adapters per Block × 6 blocks total): ~2-3M
+#   - LoRA on DGTRS-CLIP: 147K
+#   - TextFusionMLP (shared): ~3.4M
+#   - GatedFusion gates + tau: 3 scalars
+#
+# StripNet pretrained on ImageNet-1K (head dropped); state-dict naming follows
+# upstream Strip-R-CNN repo (`conv_spatial1/2`).
+
+include 'conf/gtauav_balanced.gin'
+
+# ---- Backbone ----
+TrainConfigGTAUAV.backbone = "stripnet"
+TrainConfigGTAUAV.stripnet_path = "nn_models/STRIPNET/stripnet_s.pth"
+TrainConfigGTAUAV.stripnet_mona_last_n_stages = 2  # Conv-MONA in stages 3 & 4 (deepest)
+
+# ---- Model overrides ----
+TrainConfigGTAUAV.shared_encoder = True   # StripNet always shared (one CNN for both branches)
+TrainConfigGTAUAV.mona_bottleneck = 64    # Conv-MONA bottleneck channels
+
+# ---- Output ----
+TrainConfigGTAUAV.output_dir = "out/gtauav/with_text_stripnet"

conf/gtauav_baseline_stripnet.gin

@@ -0,0 +1,8 @@
+# GTA-UAV Baseline (StripNet backbone): no text fusion. Reference R@1 for
+# computing Δ R@1 against gtauav_balanced_stripnet.gin.
+
+include 'conf/gtauav_balanced_stripnet.gin'
+
+TrainConfigGTAUAV.baseline_mode = True
+TrainConfigGTAUAV.output_dir = "out/gtauav/baseline_stripnet"
+TrainConfigGTAUAV.use_gradcam = False

src/models/asymmetric_encoder.py

@@ -28,6 +28,8 @@ from safetensors.torch import load_file as load_safetensors
 from src.models.adapters import inject_lora_into_dgtrs, inject_mona_into_dinov3
 from src.models.dgtrs.model import DGTRSTextEncoder, load_dgtrs_text_encoder, tokenize_dgtrs
 from src.models.dual_encoder import GatedFusion, ProjectionHead
+from src.models.stripnet import inject_conv_mona_into_stripnet
+from src.models.stripnet_encoder import StripNetEncoder
 
 
 # ---------------------------------------------------------------------------
@@ -302,15 +304,30 @@ class AsymmetricEncoder(nn.Module):
         mona_last_n_blocks: int = 24,
         lora_rank: int = 4,
         device: str = "cuda",
+        backbone: str = "dinov3",
+        stripnet_path: str = "nn_models/STRIPNET/stripnet_s.pth",
+        stripnet_mona_last_n_stages: int = 2,
     ) -> None:
         super().__init__()
-        self.embed_dim = self.DINO_DIM  # native 1024, no projection
+        self.embed_dim = self.DINO_DIM  # native 1024 (StripNet projects 512 -> 1024)
         self.baseline_mode = baseline_mode
         self.shared_encoder = shared_encoder
+        self.backbone = backbone
         self.device = device
 
         # Image encoder(s) (frozen + MONA adapters).
-        if shared_encoder:
+        if backbone == "stripnet":
+            # StripNet always operates as shared encoder (one CNN for both branches).
+            self.shared_encoder = True
+            self.image_encoder = StripNetEncoder(checkpoint_path=stripnet_path, out_dim=self.DINO_DIM)
+            self._freeze(self.image_encoder.backbone)
+            inject_conv_mona_into_stripnet(
+                self.image_encoder.backbone,
+                bottleneck=mona_bottleneck,
+                last_n_stages=stripnet_mona_last_n_stages,
+            )
+            LOGGER.info("StripNet backbone: shared encoder, projection 512 -> %d", self.DINO_DIM)
+        elif shared_encoder:
             self.image_encoder = DINOv3ViT.from_pretrained(dino_web_path)
             self._freeze(self.image_encoder)
             inject_mona_into_dinov3(self.image_encoder, bottleneck=mona_bottleneck, last_n_blocks=mona_last_n_blocks)

src/models/stripnet/__init__.py

@@ -0,0 +1,9 @@
+from src.models.stripnet.model import StripNet, get_stripnet_small, load_stripnet_small_pretrained
+from src.models.stripnet.conv_mona import inject_conv_mona_into_stripnet
+
+__all__ = [
+    "StripNet",
+    "get_stripnet_small",
+    "load_stripnet_small_pretrained",
+    "inject_conv_mona_into_stripnet",
+]

src/models/stripnet/conv_mona.py

@@ -0,0 +1,106 @@
+"""Conv-MONA: 2D adaptation of MONA (CVPR 2025) for hierarchical CNN backbones.
+
+MONA paper applies sequence-form adapters after MSA / MLP in ViT blocks. Here we
+mirror that idea in [B, C, H, W] form: BN → 1×1 Down(C→bn) → multi-scale DWConv
+{3,5,7} mean → +residual → GELU → 1×1 Up(bn→C). Layer scale (γ) channel-wise,
+init 1e-6 for near-identity start. Two adapters per StripNet Block: post-attn
+and post-mlp.
+"""
+from __future__ import annotations
+
+import logging
+import torch
+import torch.nn as nn
+
+from src.models.stripnet.model import StripNet, Block
+
+LOGGER = logging.getLogger("caption_test.stripnet.adapters")
+
+
+class ConvMona(nn.Module):
+    """Single Conv-MONA adapter.
+
+    Args:
+        dim: input channel dim.
+        bottleneck: bottleneck channel dim (e.g. 64).
+        gamma_init: layer-scale init value (1e-6 for near-identity at start).
+    """
+
+    def __init__(self, dim: int, bottleneck: int = 64, gamma_init: float = 1e-6) -> None:
+        super().__init__()
+        self.norm = nn.BatchNorm2d(dim)
+        self.down = nn.Conv2d(dim, bottleneck, kernel_size=1, bias=True)
+        self.dw3 = nn.Conv2d(bottleneck, bottleneck, kernel_size=3, padding=1, groups=bottleneck, bias=True)
+        self.dw5 = nn.Conv2d(bottleneck, bottleneck, kernel_size=5, padding=2, groups=bottleneck, bias=True)
+        self.dw7 = nn.Conv2d(bottleneck, bottleneck, kernel_size=7, padding=3, groups=bottleneck, bias=True)
+        self.act = nn.GELU()
+        self.up = nn.Conv2d(bottleneck, dim, kernel_size=1, bias=True)
+        # Channel-wise layer scale (γ), broadcast across H, W.
+        self.gamma = nn.Parameter(gamma_init * torch.ones(dim), requires_grad=True)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        h = self.norm(x)
+        h = self.down(h)
+        h = (self.dw3(h) + self.dw5(h) + self.dw7(h)) / 3.0 + h
+        h = self.act(h)
+        h = self.up(h)
+        return self.gamma.view(1, -1, 1, 1) * h
+
+
+def _patched_block_forward(block: Block, mona_attn: ConvMona, mona_mlp: ConvMona):
+    """Closure that wraps a Block.forward with two Conv-MONA residuals."""
+    orig_attn = block.attn
+    orig_mlp = block.mlp
+    orig_norm1 = block.norm1
+    orig_norm2 = block.norm2
+    orig_drop = block.drop_path
+    ls1 = block.layer_scale_1
+    ls2 = block.layer_scale_2
+
+    def forward(x: torch.Tensor) -> torch.Tensor:
+        x = x + orig_drop(ls1.unsqueeze(-1).unsqueeze(-1) * orig_attn(orig_norm1(x))) + mona_attn(x)
+        x = x + orig_drop(ls2.unsqueeze(-1).unsqueeze(-1) * orig_mlp(orig_norm2(x))) + mona_mlp(x)
+        return x
+
+    return forward
+
+
+def inject_conv_mona_into_stripnet(
+    model: StripNet,
+    bottleneck: int = 64,
+    last_n_stages: int = 2,
+    use_bf16: bool = False,
+) -> int:
+    """Inject Conv-MONA adapters into the deepest `last_n_stages` of StripNet.
+
+    Each Block in the targeted stages gets two adapters (post-attn, post-mlp).
+    Returns the number of adapters injected.
+
+    Stages are 1-indexed in StripNet (block1..block4). With `last_n_stages=2`
+    we adapt block3 and block4 — the deepest, semantically richest features.
+    """
+    n_stages = model.num_stages
+    target_stages = list(range(max(1, n_stages - last_n_stages + 1), n_stages + 1))
+    n_added = 0
+
+    for stage_idx in target_stages:
+        blocks: nn.ModuleList = getattr(model, f"block{stage_idx}")
+        dim = model.embed_dims[stage_idx - 1]
+        for blk_idx, block in enumerate(blocks):
+            mona_a = ConvMona(dim=dim, bottleneck=bottleneck)
+            mona_m = ConvMona(dim=dim, bottleneck=bottleneck)
+            if use_bf16:
+                mona_a.to(dtype=torch.bfloat16)
+                mona_m.to(dtype=torch.bfloat16)
+            # Register as submodules so they get moved by .to(device) / .train() etc.
+            block.add_module(f"mona_attn", mona_a)
+            block.add_module(f"mona_mlp", mona_m)
+            block.forward = _patched_block_forward(block, mona_a, mona_m)
+            n_added += 2
+
+    n_trainable = sum(p.numel() for p in model.parameters() if p.requires_grad)
+    LOGGER.info(
+        "🔧 Conv-MONA injected: %d adapters in stages %s, %d trainable params (bottleneck=%d)",
+        n_added, target_stages, n_trainable, bottleneck,
+    )
+    return n_added

src/models/stripnet/model.py

@@ -0,0 +1,253 @@
+"""StripNet (small) backbone — adapted from Strip-R-CNN (HVision-NKU).
+
+Self-contained: no external utils. State-dict naming follows the upstream
+ImageNet-pretrained checkpoint (`conv_spatial1/2` for the strip kernels).
+"""
+from __future__ import annotations
+
+import logging
+import math
+from functools import partial
+from pathlib import Path
+from typing import List
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+LOGGER = logging.getLogger("caption_test.stripnet")
+
+
+def _to_2tuple(x):
+    if isinstance(x, (tuple, list)):
+        return tuple(x)
+    return (x, x)
+
+
+def drop_path(x: torch.Tensor, drop_prob: float = 0.0, training: bool = False) -> torch.Tensor:
+    if drop_prob == 0.0 or not training:
+        return x
+    keep = 1.0 - drop_prob
+    shape = (x.shape[0],) + (1,) * (x.ndim - 1)
+    rand = x.new_empty(shape).bernoulli_(keep)
+    if keep > 0:
+        rand.div_(keep)
+    return x * rand
+
+
+class DropPath(nn.Module):
+    def __init__(self, p: float = 0.0) -> None:
+        super().__init__()
+        self.p = p
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return drop_path(x, self.p, self.training)
+
+
+class DWConv(nn.Module):
+    def __init__(self, dim: int) -> None:
+        super().__init__()
+        self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.dwconv(x)
+
+
+class Mlp(nn.Module):
+    def __init__(self, in_features: int, hidden_features: int, drop: float = 0.0) -> None:
+        super().__init__()
+        self.fc1 = nn.Conv2d(in_features, hidden_features, 1)
+        self.dwconv = DWConv(hidden_features)
+        self.act = nn.GELU()
+        self.fc2 = nn.Conv2d(hidden_features, in_features, 1)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = self.fc1(x)
+        x = self.dwconv(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class StripGatingUnit(nn.Module):
+    """Strip spatial gating: 5x5 DWConv -> (1, k2) -> (k2, 1) -> 1x1 -> gate."""
+
+    def __init__(self, dim: int, k1: int, k2: int) -> None:
+        super().__init__()
+        self.conv0 = nn.Conv2d(dim, dim, 5, padding=2, groups=dim)
+        # Names match upstream pretrained checkpoint: conv_spatial1 / conv_spatial2.
+        self.conv_spatial1 = nn.Conv2d(dim, dim, kernel_size=(k1, k2), stride=1,
+                                       padding=(k1 // 2, k2 // 2), groups=dim)
+        self.conv_spatial2 = nn.Conv2d(dim, dim, kernel_size=(k2, k1), stride=1,
+                                       padding=(k2 // 2, k1 // 2), groups=dim)
+        self.conv1 = nn.Conv2d(dim, dim, 1)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        attn = self.conv0(x)
+        attn = self.conv_spatial1(attn)
+        attn = self.conv_spatial2(attn)
+        attn = self.conv1(attn)
+        return x * attn
+
+
+class StripAttention(nn.Module):
+    def __init__(self, dim: int, k1: int, k2: int) -> None:
+        super().__init__()
+        self.proj_1 = nn.Conv2d(dim, dim, 1)
+        self.activation = nn.GELU()
+        self.spatial_gating_unit = StripGatingUnit(dim, k1, k2)
+        self.proj_2 = nn.Conv2d(dim, dim, 1)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        residual = x
+        x = self.proj_1(x)
+        x = self.activation(x)
+        x = self.spatial_gating_unit(x)
+        x = self.proj_2(x)
+        return x + residual
+
+
+class Block(nn.Module):
+    def __init__(self, dim: int, mlp_ratio: float, k1: int, k2: int, drop: float, drop_path: float) -> None:
+        super().__init__()
+        self.norm1 = nn.BatchNorm2d(dim)
+        self.norm2 = nn.BatchNorm2d(dim)
+        self.attn = StripAttention(dim, k1, k2)
+        self.drop_path = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
+        self.mlp = Mlp(dim, int(dim * mlp_ratio), drop=drop)
+        ls_init = 1e-2
+        self.layer_scale_1 = nn.Parameter(ls_init * torch.ones(dim), requires_grad=True)
+        self.layer_scale_2 = nn.Parameter(ls_init * torch.ones(dim), requires_grad=True)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = x + self.drop_path(
+            self.layer_scale_1.unsqueeze(-1).unsqueeze(-1) * self.attn(self.norm1(x))
+        )
+        x = x + self.drop_path(
+            self.layer_scale_2.unsqueeze(-1).unsqueeze(-1) * self.mlp(self.norm2(x))
+        )
+        return x
+
+
+class OverlapPatchEmbed(nn.Module):
+    def __init__(self, patch_size: int, stride: int, in_chans: int, embed_dim: int) -> None:
+        super().__init__()
+        ph, pw = _to_2tuple(patch_size)
+        self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=(ph, pw), stride=stride,
+                              padding=(ph // 2, pw // 2))
+        self.norm = nn.BatchNorm2d(embed_dim)
+
+    def forward(self, x: torch.Tensor) -> tuple[torch.Tensor, int, int]:
+        x = self.proj(x)
+        _, _, H, W = x.shape
+        x = self.norm(x)
+        return x, H, W
+
+
+class StripNet(nn.Module):
+    """Strip-R-CNN backbone: 4-stage hierarchical CNN with strip-shaped DWConv attention.
+
+    Output: list of [B, C_i, H/s_i, W/s_i] per stage. Use `forward_last_features` for
+    the deepest stage only.
+    """
+
+    def __init__(
+        self,
+        embed_dims: List[int] = [64, 128, 320, 512],
+        mlp_ratios: List[int] = [8, 8, 4, 4],
+        k1s: List[int] = [1, 1, 1, 1],
+        k2s: List[int] = [19, 19, 19, 19],
+        depths: List[int] = [2, 2, 4, 2],
+        drop_rate: float = 0.1,
+        drop_path_rate: float = 0.15,
+        in_chans: int = 3,
+    ) -> None:
+        super().__init__()
+        self.depths = depths
+        self.num_stages = len(depths)
+        self.embed_dims = embed_dims
+
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
+        cur = 0
+        for i in range(self.num_stages):
+            patch_embed = OverlapPatchEmbed(
+                patch_size=7 if i == 0 else 3,
+                stride=4 if i == 0 else 2,
+                in_chans=in_chans if i == 0 else embed_dims[i - 1],
+                embed_dim=embed_dims[i],
+            )
+            block = nn.ModuleList([
+                Block(dim=embed_dims[i], mlp_ratio=mlp_ratios[i], k1=k1s[i], k2=k2s[i],
+                      drop=drop_rate, drop_path=dpr[cur + j])
+                for j in range(depths[i])
+            ])
+            norm = nn.LayerNorm(embed_dims[i], eps=1e-6)
+            cur += depths[i]
+            setattr(self, f"patch_embed{i + 1}", patch_embed)
+            setattr(self, f"block{i + 1}", block)
+            setattr(self, f"norm{i + 1}", norm)
+
+    def forward_features(self, x: torch.Tensor) -> List[torch.Tensor]:
+        B = x.shape[0]
+        outs: List[torch.Tensor] = []
+        for i in range(self.num_stages):
+            patch_embed = getattr(self, f"patch_embed{i + 1}")
+            block = getattr(self, f"block{i + 1}")
+            norm = getattr(self, f"norm{i + 1}")
+            x, H, W = patch_embed(x)
+            for blk in block:
+                x = blk(x)
+            x = x.flatten(2).transpose(1, 2)
+            x = norm(x)
+            x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
+            outs.append(x)
+        return outs
+
+    def forward_last_features(self, x: torch.Tensor) -> torch.Tensor:
+        return self.forward_features(x)[-1]
+
+
+def get_stripnet_small() -> StripNet:
+    return StripNet(
+        embed_dims=[64, 128, 320, 512],
+        mlp_ratios=[8, 8, 4, 4],
+        k1s=[1, 1, 1, 1],
+        k2s=[19, 19, 19, 19],
+        depths=[2, 2, 4, 2],
+        drop_rate=0.1,
+        drop_path_rate=0.15,
+    )
+
+
+def load_stripnet_small_pretrained(checkpoint_path: str | Path) -> StripNet:
+    """Build StripNet-small and load ImageNet-pretrained weights.
+
+    Strips the classification `head.*` keys. Tolerates missing/extra keys
+    (norm{N}.* are LayerNorm here vs BatchNorm in some forks — we keep LN).
+    """
+    LOGGER.info("📐 Loading StripNet-small from %s", checkpoint_path)
+    model = get_stripnet_small()
+    raw = torch.load(checkpoint_path, map_location="cpu", weights_only=False)
+    state = raw.get("state_dict", raw) if isinstance(raw, dict) else raw
+
+    # Drop classification head + the BN-form norm{N} keys if present (we use LN here).
+    drop_prefixes = ("head.",)
+    cleaned = {k: v for k, v in state.items() if not any(k.startswith(p) for p in drop_prefixes)}
+
+    # The pretrained checkpoint stores norm{N} as BatchNorm2d (running_mean/var/num_batches_tracked).
+    # Our code uses LayerNorm at this position. Strip BN running stats if found; copy weight/bias.
+    for n in (1, 2, 3, 4):
+        for suffix in ("running_mean", "running_var", "num_batches_tracked"):
+            cleaned.pop(f"norm{n}.{suffix}", None)
+
+    missing, unexpected = model.load_state_dict(cleaned, strict=False)
+    if missing:
+        LOGGER.info("StripNet missing keys (expected for newly-init layers): %d", len(missing))
+    if unexpected:
+        LOGGER.info("StripNet unexpected keys (ignored): %d", len(unexpected))
+    LOGGER.info("📐 StripNet-small loaded: %d params", sum(p.numel() for p in model.parameters()))
+    return model

src/models/stripnet_encoder.py

@@ -0,0 +1,48 @@
+"""StripNet image encoder wrapper for the caption-test pipeline.
+
+Exposes the same interface as DINOv3ViT: `forward(images) -> [B, embed_dim]`.
+StripNet's deepest stage produces [B, 512, H/32, W/32]; we apply global average
+pooling (GAP) and project to the target retrieval dimension via Linear(512→1024)
+to match DINOv3 native dim and keep TextFusionMLP unchanged.
+"""
+from __future__ import annotations
+
+import logging
+import torch
+import torch.nn as nn
+
+from src.models.stripnet import StripNet, load_stripnet_small_pretrained
+
+LOGGER = logging.getLogger("caption_test.stripnet_encoder")
+
+
+class StripNetEncoder(nn.Module):
+    """StripNet-small + GAP + projection to `out_dim`.
+
+    Frozen backbone (BatchNorm in eval mode); only the projection head and
+    any injected Conv-MONA adapters are trainable.
+    """
+
+    LAST_STAGE_DIM = 512  # StripNet-small last stage embed dim
+
+    def __init__(self, checkpoint_path: str, out_dim: int = 1024) -> None:
+        super().__init__()
+        self.out_dim = out_dim
+        self.backbone: StripNet = load_stripnet_small_pretrained(checkpoint_path)
+        self.pool = nn.AdaptiveAvgPool2d(1)
+        self.projection = nn.Linear(self.LAST_STAGE_DIM, out_dim)
+        nn.init.trunc_normal_(self.projection.weight, std=0.02)
+        nn.init.zeros_(self.projection.bias)
+
+    def train(self, mode: bool = True):
+        """Override: keep frozen backbone in eval mode (BN running stats stable)."""
+        super().train(mode)
+        # Frozen backbone always in eval; trainable adapters/projection follow `mode`.
+        if not any(p.requires_grad for p in self.backbone.parameters()):
+            self.backbone.eval()
+        return self
+
+    def forward(self, images: torch.Tensor) -> torch.Tensor:
+        feat = self.backbone.forward_last_features(images)  # [B, 512, H/32, W/32]
+        pooled = self.pool(feat).flatten(1)                  # [B, 512]
+        return self.projection(pooled)                        # [B, out_dim]

src/training/train_gtauav.py

@@ -90,6 +90,10 @@ class TrainConfigGTAUAV:
     mona_bottleneck: int = 64
     mona_last_n_blocks: int = 12  # inject adapters only in last 12 of 24 ViT blocks
     gradient_checkpointing: bool = True  # trade compute for VRAM (allows larger batch)
+    # StripNet backbone option (replaces DINOv3 when backbone="stripnet").
+    backbone: str = "dinov3"  # "dinov3" or "stripnet"
+    stripnet_path: str = "nn_models/STRIPNET/stripnet_s.pth"
+    stripnet_mona_last_n_stages: int = 2  # Conv-MONA in last N of 4 StripNet stages
 
     # Training.
     resume_from: str | None = None  # path to checkpoint for resuming
@@ -564,7 +568,10 @@ def train(cfg: TrainConfigGTAUAV) -> None:
         start_epoch = resume_ckpt.get("epoch", -1) + 1
     else:
         mode_str = "baseline (no text)" if cfg.baseline_mode else "with text (L1/L2/L3)"
-        enc_str = "shared DINOv3 WEB" if cfg.shared_encoder else "asymmetric (WEB + SAT)"
+        if cfg.backbone == "stripnet":
+            enc_str = "StripNet-small (shared, 512→1024 proj)"
+        else:
+            enc_str = "shared DINOv3 WEB" if cfg.shared_encoder else "asymmetric (WEB + SAT)"
         LOGGER.info("Building model — %s, %s", mode_str, enc_str)
         model = AsymmetricEncoder(
             dino_web_path=cfg.dino_web_path,
@@ -576,11 +583,15 @@ def train(cfg: TrainConfigGTAUAV) -> None:
             mona_bottleneck=cfg.mona_bottleneck,
             mona_last_n_blocks=cfg.mona_last_n_blocks,
             device=cfg.device,
+            backbone=cfg.backbone,
+            stripnet_path=cfg.stripnet_path,
+            stripnet_mona_last_n_stages=cfg.stripnet_mona_last_n_stages,
         ).to(cfg.device)
         LOGGER.info("embed_dim=%d", model.embed_dim)
 
     # --- Gradient checkpointing (trade compute for VRAM) ---
-    if cfg.gradient_checkpointing:
+    # StripNet doesn't expose set_gradient_checkpointing — skip silently.
+    if cfg.gradient_checkpointing and cfg.backbone == "dinov3":
         if cfg.shared_encoder:
             model.image_encoder.set_gradient_checkpointing(True)
         else:
@@ -589,6 +600,10 @@ def train(cfg: TrainConfigGTAUAV) -> None:
         if model.text_encoder is not None:
             model.text_encoder.transformer.gradient_checkpointing = True
         LOGGER.info("Gradient checkpointing enabled (DINOv3 + DGTRS)")
+    elif cfg.gradient_checkpointing and cfg.backbone == "stripnet":
+        if model.text_encoder is not None:
+            model.text_encoder.transformer.gradient_checkpointing = True
+        LOGGER.info("Gradient checkpointing enabled (DGTRS only; StripNet doesn't support)")
 
     n_trainable = sum(p.numel() for p in model.trainable_parameters())
     n_total = sum(p.numel() for p in model.parameters())