Official PyTorch implementation of "Learning Not to Reconstruct Anomalies"

This is the implementation of the paper "Learning Not to Reconstruct Anomalies" (BMVC 2021).

Dependencies

• Python 3.6
• PyTorch = 1.7.0
• Numpy
• Sklearn

Datasets

• USCD Ped2 [dataset]
• CUHK Avenue [dataset]
• ShanghaiTech [dataset]
• CIFAR-100 (for patch based pseudo anomalies)
• ImageNet (for patch based pseudo anomalies)

Download the datasets into dataset folder, like ./dataset/ped2/, ./dataset/avenue/, ./dataset/shanghai/, ./dataset/cifar100/, ./dataset/imagenet/

Training

git clone https://github.com/aseuteurideu/LearningNotToReconstructAnomalies

• Training baseline

python train.py --dataset_type ped2

• Training patch based model

python train.py --dataset_type ped2 --pseudo_anomaly_cifar_inpainting_smoothborder 0.2 --max_size 0.5 --max_move 10

• Training skip frame based model

python train.py --dataset_type ped2 --pseudo_anomaly_jump_inpainting 0.2 --jump 2 3 4 5

Select --dataset_type from ped2, avenue, or shanghai.

For more details, check train.py

Pre-trained models

• Model in Table 1

• Various patch based models on Ped2 (Fig. 5(c))

Evaluation

• Test the model

python evaluate.py --dataset_type ped2 --model_dir path_to_weight_file.pth

• Test the model and save result image

python evaluate.py --dataset_type ped2 --model_dir path_to_weight_file.pth --img_dir folder_path_to_save_image_results

• Test the model and generate demonstration video frames

python evaluate.py --dataset_type ped2 --model_dir path_to_weight_file.pth --vid_dir folder_path_to_save_video_results

Then compile the frames into video. For example, to compile the first video in ubuntu:

ffmpeg -framerate 10 -i frame_00_%04d.png -c:v libx264 -profile:v high -crf 20 -pix_fmt yuv420p video_00.mp4

Bibtex

@inproceedings{astrid2021learning,
  title={Learning Memory-guided Normality for Anomaly Detection},
  author={Astrid, Marcella and Zaheer, Muhammad Zaigham and Lee, Jae-Yeong and Lee, Seung-Ik},
  booktitle={BMVC},
  year={2021}
}

Acknowledgement

The code is built on top of code provided by Park et al. [ github ] and Gong et al. [ github ]