-
Notifications
You must be signed in to change notification settings - Fork 15
Evaluate usability of GANs, flow based models
Diana Davletshina edited this page May 27, 2019
·
3 revisions
-
DEEP LEARNING FOR ANOMALY DETECTION: A SURVEY:
- Overview for different anomaly detection techniques using deep learning
- "We have grouped state-of-the-art deep anomaly detection research techniques into different categories based on the underlying assumptions and approach adopted. Within each category, we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. Besides, for each category, we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains."
-
Medium: GAN for unsupervised anomaly detection on X-ray images
- "With this article, now you have a better idea of how not to build an anomaly detection with GAN and hopefully you might have a better idea on how to do it."
-
EFFICIENT GAN-BASED ANOMALY DETECTION:
- "Generative adversarial networks (GANs) are able to model the complex high dimensional distributions of real-world data, which suggests they could be effective for anomaly detection."
- "We leverage recently developed GAN models for anomaly detection, and achieve state-of-the-art performance on image and net- work intrusion datasets, while being several hundred-fold faster at test time than the only published GAN-based method."
- "a GAN that has been well-trained to fit the distribution of normal samples should be able to reconstruct such a normal sample from a certain latent representation and also discriminate the sample as coming from the true data distribution. However, as GANs only implicitly model the data distribution, using them for anomaly detection necessitates a costly optimization procedure to recover the latent representation of a given input example, making this an impractical approach for large datasets or real-time applications."
-
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery:
- "Here, we perform unsupervised learning to identify anomalies in imaging data as candidates for markers. We propose AnoGAN, a deep convolutional generative adversarial network to learn a manifold of normal anatomical variability, accompanying a novel anomaly scoring scheme based on the mapping from image space to a la- tent space. Applied to new data, the model labels anomalies, and scores image patches indicating their fit into the learned distribution. Results on optical coherence tomography images of the retina demonstrate that the approach correctly identifies anomalous images, such as images containing retinal fluid or hyperreflective foci."
- "By concurrently training a generative model and a discriminator, we enable the identification of anomalies on unseen data based on unsupervised training of a model on healthy data. Results show that our approach is able to detect different known anomalies, such as retinal fluid and HRF, which have never been seen during training. Therefore, the model is expected to be capable to discover novel anomalies. While quantitative evaluation based on a subset of anomaly classes is limited, since false positives do not take novel anomalies into account, results demonstrate good sensitivity and the capability to segment anomalies. "
-
- "In this work, we investigate the use of GANs for producing chest X-ray images to augment a dataset. This dataset is then used to train a convolutional neural network to classify images for cardiovascular abnormalities. We compare our augmentation strategy with traditional data augmentation and show higher accuracy for normal vs abnormal classification in chest X-rays."
-
- GANs can solve the problem of a small train set by generating sample images. The following example demonstrates usage of GANs for medical liver images.