Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies

• URL: http://arxiv.org/abs/2203.13716v1
• Date: Fri, 25 Mar 2022 15:37:52 GMT
• Title: Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies
• Authors: Muhammad Zaigham Zaheer, Jin Ha Lee, Arif Mahmood, Marcella Astrid, Seung-Ik Lee
• Abstract summary: anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. We propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions.
• Score: 22.48845887819345
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. Attributed to the adversarial training, performance of such models fluctuates drastically with each training step, making it difficult to halt the training at an optimal point. In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions. For this purpose, we propose a method that utilizes the current state as well as an old state of the same generator to create good and bad quality reconstruction examples. The discriminator is trained on these examples to detect the subtle distortions that are often present in the reconstructions of anomalous data. In addition, we propose an efficient generic criterion to stop the training of our model, ensuring elevated performance. Extensive experiments performed on six datasets across multiple domains including image and video based anomaly detection, medical diagnosis, and network security, have demonstrated excellent performance of our approach.

Related papers

• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representations [8.915958745269442]
  Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these techniques often face practical problems such as memory inefficiency and the requirement of sufficient data for training. We propose a few-shot anomaly detection method that integrates adversarial training loss to obtain more robust and generalized feature representations.
  arXiv  Detail & Related papers  (2023-12-04T09:45:02Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• ARES: Locally Adaptive Reconstruction-based Anomaly Scoring [25.707159917988733]
  We show that anomaly scoring function is not adaptive to the natural variation in reconstruction error across the range of normal samples. We propose a novel Adaptive Reconstruction Error-based Scoring approach, which adapts its scoring based on the local behaviour of reconstruction error over the latent space.
  arXiv  Detail & Related papers  (2022-06-15T15:35:12Z)
• Learning perturbation sets for robust machine learning [97.6757418136662]
  We use a conditional generator that defines the perturbation set over a constrained region of the latent space. We measure the quality of our learned perturbation sets both quantitatively and qualitatively. We leverage our learned perturbation sets to train models which are empirically and certifiably robust to adversarial image corruptions and adversarial lighting variations.
  arXiv  Detail & Related papers  (2020-07-16T16:39:54Z)
• Interpreting Rate-Distortion of Variational Autoencoder and Using Model Uncertainty for Anomaly Detection [5.491655566898372]
  We build a scalable machine learning system for unsupervised anomaly detection via representation learning. We revisit VAE from the perspective of information theory to provide some theoretical foundations on using the reconstruction error. We show empirically the competitive performance of our approach on benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-05T00:03:48Z)
• Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm [15.898383112569237]
  A popular method for anomaly detection is to use the generator of an adversarial network to formulate anomaly scores. We propose a framework that effectively generates stable results across a wide range of training steps. Our model achieves a frame-level AUC of 98.1%, surpassing recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-16T13:48:58Z)
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders [51.691585766702744]
  We propose a variant of Adversarial Autoencoder which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We put forward an alternative measure of anomaly score to replace the reconstruction-based metric. Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.
  arXiv  Detail & Related papers  (2020-03-24T08:26:58Z)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)
• Regularized Cycle Consistent Generative Adversarial Network for Anomaly Detection [5.457279006229213]
  We propose a new Regularized Cycle Consistent Generative Adversarial Network (RCGAN) in which deep neural networks are adversarially trained to better recognize anomalous samples. Experimental results on both real-world and synthetic data show that our model leads to significant and consistent improvements on previous anomaly detection benchmarks.
  arXiv  Detail & Related papers  (2020-01-18T03:35:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.