Perceptual Image Anomaly Detection
arXiv:1909.05904 · doi:10.1007/978-3-030-41404-7_12
Abstract
We present a novel method for image anomaly detection, where algorithms that use samples drawn from some distribution of "normal" data, aim to detect out-of-distribution (abnormal) samples. Our approach includes a combination of encoder and generator for mapping an image distribution to a predefined latent distribution and vice versa. It leverages Generative Adversarial Networks to learn these data distributions and uses perceptual loss for the detection of image abnormality. To accomplish this goal, we introduce a new similarity metric, which expresses the perceived similarity between images and is robust to changes in image contrast. Secondly, we introduce a novel approach for the selection of weights of a multi-objective loss function (image reconstruction and distribution mapping) in the absence of a validation dataset for hyperparameter tuning. After training, our model measures the abnormality of the input image as the perceptual dissimilarity between it and the closest generated image of the modeled data distribution. The proposed approach is extensively evaluated on several publicly available image benchmarks and achieves state-of-the-art performance.
arXiv commentThe final authenticated publication is available online at https://doi.org/10.1007/978-3-030-41404-7_12
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Survey on Deep Learning in Medical Image Analysis
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- Deep Learning for Anomaly Detection: A Survey
- Efficient GAN-Based Anomaly Detection
- Texture Synthesis Using Convolutional Neural Networks
- Generative Probabilistic Novelty Detection with Adversarial Autoencoders
- Denoising Autoencoders for Overgeneralization in Neural Networks