Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+tags:
+  - rgb-thermal
+  - semantic-segmentation
+  - segformer
+  - defense
+  - anima
+datasets:
+  - MFNet
+  - PST900
+  - FMB
+metrics:
+  - mIoU
+pipeline_tag: image-segmentation
+---
+
+# DEF-rtfdnet: RTFDNet for Robust RGB-T Segmentation
+
+ANIMA Defense Module implementing **RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation** (ArXiv 2603.09149).
+
+## Architecture
+
+- **Backbone**: BIMixVisionTransformer (dual-stream SegFormer MiT-B2, 50.4M params)
+- **Fusion**: EAEF_clip (CLIP-style cross-modal alignment) + gated feature fusion at each of 4 stages
+- **Losses**: CE + Modal CE + AKD (feature distillation) + RegionL1 (logit distillation)
+- **Input**: 6-channel tensor (RGB + Thermal), 480x640 or 512x512
+
+## Results
+
+| Dataset | Classes | mIoU | Accuracy |
+|---------|---------|------|----------|
+| MFNet   | 9       | 0.929 | 0.979   |
+| PST900  | 5       | training... | - |
+| FMB     | 14      | training... | - |
+
+## Exports
+
+Each dataset variant includes:
+- `model.safetensors` - PyTorch weights
+- `model.onnx` - ONNX (opset 17)
+- `model_fp16.trt` - TensorRT FP16
+- `model_fp32.trt` - TensorRT FP32
+
+## Usage
+
+```python
+from def_rtfdnet.model import build_rtfdnet
+model = build_rtfdnet(variant='mit_b2', num_classes=9, pretrained='models/mit_b2.pth')
+```
+
+## Citation
+
+```bibtex
+@article{tan2026rtfdnet,
+  title={RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation},
+  author={Tan, Kunyu and Liang, Mingjian},
+  journal={arXiv preprint arXiv:2603.09149},
+  year={2026}
+}
+```
+
+Built with ANIMA by Robot Flow Labs