DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
This work is significant for industries requiring automated defect detection, as it improves the ability to identify small, confined anomalies in manufacturing products without prior knowledge of anomaly types.
This paper addresses the challenge of unsupervised anomaly segmentation, particularly for small anomalies in images. The authors propose a method that uses a multi-scale regional feature generator and a convolutional autoencoder for fast feature reconstruction, achieving state-of-the-art performance on several benchmark datasets.
Automatic detecting anomalous regions in images of objects or textures without priors of the anomalies is challenging, especially when the anomalies appear in very small areas of the images, making difficult-to-detect visual variations, such as defects on manufacturing products. This paper proposes an effective unsupervised anomaly segmentation approach that can detect and segment out the anomalies in small and confined regions of images. Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image. The regional representations not only describe the local characteristics of corresponding regions but also encode their multiple spatial context information, making them discriminative and very beneficial for anomaly detection. Leveraging these descriptive regional features, we then design a deep yet efficient convolutional autoencoder and detect anomalous regions within images via fast feature reconstruction. Our method is simple yet effective and efficient. It advances the state-of-the-art performances on several benchmark datasets and shows great potential for real applications.