Lightweight Masked Reconstruction for Real-Time Sensor-Driven Anomaly Detection in Industrial IoT

🌐 中文

📄 Paper | ⚡ C++ Implementation

pytorch lightning anomalib

📊 Performance

AeBAD-S (Aero-Engine Blade)

MVTec AD

Jetson AGX Xavier Edge Deployment

🚀 Quick Start

⌨️ Training

# Sync environment (first time only)
uv sync --extra cu126
# MVTec (single category)
uv run python tools\limr\train.py --dataset mvtec --root ./datasets/MVTec --category bottle \
 --image-size 224 --backbone resnet50 --alpha 1.75 --epochs 200
# AeBAD-S
uv run python tools\limr\train.py --dataset aebad_s --root I:\exp\datasets\AeBAD\AeBAD_S \
 --category AeBAD_S --image-size 256 --backbone resnet34 --alpha 1.75 \
 --fpn-output-dim 64 128 256 512 --block-dropout 0.0 --block-ffn-dropout 0.0 \
 --block-attn-dropout 0.0 --frozen-stages 3 --epochs 200 --seed 54
# AeBAD-V
uv run python tools\limr\train.py --dataset aebad_v --root I:\exp\datasets\AeBAD\AeBAD_V \
 --category AeBAD_V --image-size 256 --backbone resnet34 --alpha 1.75 \
 --fpn-output-dim 64 128 256 512 --block-dropout 0.0 --block-ffn-dropout 0.0 \
 --block-attn-dropout 0.0 --frozen-stages 3 --epochs 200 --seed 54
# RealIAD
uv run python tools\limr\train.py --dataset realiad --root ./datasets/RealIAD --category <category> \
 --realiad-resolution 256 --realiad-json ./datasets/RealIAD/RealIAD.json
# VISA
uv run python tools\limr\train.py --dataset visa --root ./datasets/VISA --category candle \
 --image-size 224 --backbone resnet50
# Folder (custom dataset)
uv run python tools\limr\train.py --dataset folder --root ./datasets/my_data \
 --folder-normal-dir normal --folder-abnormal-dir abnormal --folder-mask-dir mask \
 --category my_dataset

⌨️ Testing

# Test anomalib checkpoint (.ckpt)
uv run python tools\limr\test.py --dataset mvtec --root ./datasets/MVTec --category bottle \
 --image-size 224 --backbone resnet50 --alpha 1.75 --checkpoint ./output_limr/xxx.ckpt
# Test original LiMR weights (.pth)
uv run python tools\limr\test.py --dataset aebad_s --root I:\exp\datasets\AeBAD\AeBAD_S \
 --category AeBAD_S --image-size 256 --backbone resnet34 --alpha 1.75 \
 --block-dropout 0.0 --block-ffn-dropout 0.0 --block-attn-dropout 0.0 \
 --frozen-stages 3 --seed 54 --original-checkpoint I:\exp\LiMR\best_student_model_175.pth

📦 Supported Datasets

⚙️ Parameter Reference

Data Parameters

Model Parameters

Training Parameters

📜 Batch Scripts

📂 Output Structure

output_limr/aebad_s/
├── LiMR/AeBAD_S/AeBAD_S/v34/
│ └── weights/
│ ├── lightning/model.ckpt # Best checkpoint
│ └── onnx/model.onnx # ONNX export
├── inference_speed.json # Inference benchmark
└── wandb/ # W&B logs (if enabled)

⚡ TensorRT High-Speed Deployment

❓ FAQ

📚 Reference

@article{liao2026limr,
 author = {Shaowei Liao and Wenyong Yu and Shaolin Liao},
 title = {Lightweight Masked Reconstruction for Real-Time Sensor-Driven
 Anomaly Detection in Industrial IoT},
 journal = {IEEE Internet of Things Journal},
 year = {2026},
 doi = {10.1109/JIOT.2026.3712733}
}

Acknowledgements