Learning Not to Reconstruct Anomalies

• URL: http://arxiv.org/abs/2110.09742v1
• Date: Tue, 19 Oct 2021 05:22:38 GMT
• Title: Learning Not to Reconstruct Anomalies
• Authors: Marcella Astrid, Muhammad Zaigham Zaheer, Jae-Yeong Lee, Seung-Ik Lee
• Abstract summary: Autoencoder (AE) is trained to reconstruct the input with training set consisting only of normal data. AE is then expected to well reconstruct the normal data while poorly reconstructing the anomalous data. We propose a novel methodology to train AEs with the objective of reconstructing only normal data, regardless of the input.
• Score: 14.632592282260363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video anomaly detection is often seen as one-class classification (OCC) problem due to the limited availability of anomaly examples. Typically, to tackle this problem, an autoencoder (AE) is trained to reconstruct the input with training set consisting only of normal data. At test time, the AE is then expected to well reconstruct the normal data while poorly reconstructing the anomalous data. However, several studies have shown that, even with only normal data training, AEs can often start reconstructing anomalies as well which depletes the anomaly detection performance. To mitigate this problem, we propose a novel methodology to train AEs with the objective of reconstructing only normal data, regardless of the input (i.e., normal or abnormal). Since no real anomalies are available in the OCC settings, the training is assisted by pseudo anomalies that are generated by manipulating normal data to simulate the out-of-normal-data distribution. We additionally propose two ways to generate pseudo anomalies: patch and skip frame based. Extensive experiments on three challenging video anomaly datasets demonstrate the effectiveness of our method in improving conventional AEs, achieving state-of-the-art performance.

Related papers

• Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection [88.34095233600719]
  FAPrompt is a novel framework designed to learn Fine-grained Abnormality Prompts for more accurate ZSAD. It substantially outperforms state-of-the-art methods by at least 3%-5% AUC/AP in both image- and pixel-level ZSAD tasks.
  arXiv  Detail & Related papers  (2024-10-14T08:41:31Z)
• Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies [17.342474659784823]
  A typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal data. We propose creating pseudo anomalies from learned adaptive noise by exploiting the weakness of AE, i.e., reconstructing anomalies too well.
  arXiv  Detail & Related papers  (2024-05-09T16:22:24Z)
• Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data [11.237938539765825]
  Autoencoder (AE) is typically trained to reconstruct the data. During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data. We propose to limit the reconstruction capability of AE by introducing a novel latent constriction loss.
  arXiv  Detail & Related papers  (2024-03-24T19:22:15Z)
• AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [59.08735812631131]
  Anomaly inspection plays an important role in industrial manufacture. Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data. We propose AnomalyDiffusion, a novel diffusion-based few-shot anomaly generation model.
  arXiv  Detail & Related papers  (2023-12-10T05:13:40Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies [13.14903445595385]
  Autoencoder (AE) is trained to reconstruct the normal only training data with the expectation that, in test time, it can poorly reconstruct the anomalous data. We propose to limit the anomaly reconstruction capability of AEs by incorporating pseudo anomalies during the training of an AE. We demonstrate the effectiveness of our proposed pseudo anomaly based training approach against several existing state-ofthe-art (SOTA) methods on three benchmark video anomaly datasets.
  arXiv  Detail & Related papers  (2023-03-19T16:19:13Z)
• Synthetic Pseudo Anomalies for Unsupervised Video Anomaly Detection: A Simple yet Efficient Framework based on Masked Autoencoder [1.9511777443446219]
  We propose a simple yet efficient framework for video anomaly detection. The pseudo anomaly samples are synthesized from only normal data by embedding random mask tokens without extra data processing. We also propose a normalcy consistency training strategy that encourages the AEs to better learn the regular knowledge from normal and corresponding pseudo anomaly data.
  arXiv  Detail & Related papers  (2023-03-09T08:33:38Z)
• Are we certain it's anomalous? [57.729669157989235]
  Anomaly detection in time series is a complex task since anomalies are rare due to highly non-linear temporal correlations. Here we propose the novel use of Hyperbolic uncertainty for Anomaly Detection (HypAD) HypAD learns self-supervisedly to reconstruct the input signal.
  arXiv  Detail & Related papers  (2022-11-16T21:31:39Z)
• Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection [16.436293069942312]
  Autoencoders (AEs) often start reconstructing anomalies as well which depletes their anomaly detection performance. We propose a temporal pseudo anomaly synthesizer that generates fake-anomalies using only normal data. An AE is then trained to maximize the reconstruction loss on pseudo anomalies while minimizing this loss on normal data.
  arXiv  Detail & Related papers  (2021-10-19T07:08:44Z)
• Explainable Deep Few-shot Anomaly Detection with Deviation Networks [123.46611927225963]
  We introduce a novel weakly-supervised anomaly detection framework to train detection models. The proposed approach learns discriminative normality by leveraging the labeled anomalies and a prior probability. Our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings.
  arXiv  Detail & Related papers  (2021-08-01T14:33:17Z)
• Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data [150.9270911031327]
  We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies.
  arXiv  Detail & Related papers  (2020-09-15T03:05:39Z)

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.