# Deep Visual Anomaly detection with Negative Learning

arXiv: https://arxiv.org/abs/2105.11058 · HTML: https://mlsanity.com/paper/2105.11058/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 24 May 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm](https://mlsanity.com/paper/2004.07657/) (2020)
- [CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection](https://mlsanity.com/paper/2011.12077/) (2020)
- [Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders](https://mlsanity.com/paper/1510.01442/) (2015)
- [A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels](https://mlsanity.com/paper/2008.11887/) (2020)
- [Autoencoding Binary Classifiers for Supervised Anomaly Detection](https://mlsanity.com/paper/1903.10709/) (2019)
- [Limiting the Reconstruction Capability of Generative Neural Network using Negative Learning](https://mlsanity.com/paper/1708.08985/) (2017)
- [Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detection](https://mlsanity.com/paper/2104.14770/) (2021)

## Built on by (most cited first, 3 of 3)

- [Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos](https://mlsanity.com/paper/2203.13704/) (2022)
- [Bidirectional Uncertainty-Based Active Learning for Open Set Annotation](https://mlsanity.com/paper/2402.15198/) (2024)
- [Supervised Anomaly Detection Method Combining Generative Adversarial Networks and Three-Dimensional Data in Vehicle Inspections](https://mlsanity.com/paper/2212.11507/) (2022)

## Abstract (arXiv)

With the increase in the learning capability of deep convolution-based architectures, various applications of such models have been proposed over time. In the field of anomaly detection, improvements in deep learning opened new prospects of exploration for the researchers whom tried to automate the labor-intensive features of data collection. First, in terms of data collection, it is impossible to anticipate all the anomalies that might exist in a given environment. Second, assuming we limit the possibilities of anomalies, it will still be hard to record all these scenarios for the sake of training a model. Third, even if we manage to record a significant amount of abnormal data, it's laborious to annotate this data on pixel or even frame level. Various approaches address the problem by proposing one-class classification using generative models trained on only normal data. In such methods, only the normal data is used, which is abundantly available and doesn't require significant human input. However, these are trained with only normal data and at the test time, given abnormal data as input, may often generate normal-looking output. This happens due to the hallucination characteristic of generative models. Next, these systems are designed to not use abnormal examples during the training. In this paper, we propose anomaly detection with negative learning (ADNL), which employs the negative learning concept for the enhancement of anomaly detection by utilizing a very small number of labeled anomaly data as compared with the normal data during training. The idea is to limit the reconstruction capability of a generative model using the given a small amount of anomaly examples. This way, the network not only learns to reconstruct normal data but also encloses the normal distribution far from the possible distribution of anomalies.