# Limiting the Reconstruction Capability of Generative Neural Network using Negative Learning

arXiv: https://arxiv.org/abs/1708.08985 · HTML: https://mlsanity.com/paper/1708.08985/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2017.

## Built on by (most cited first, 16 of 16)

- [SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation](https://mlsanity.com/paper/2104.14812/) (2021)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles](https://mlsanity.com/paper/2207.10172/) (2022)
- [Learning Not to Reconstruct Anomalies](https://mlsanity.com/paper/2110.09742/) (2021)
- [Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2110.09768/) (2021)
- [Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects](https://mlsanity.com/paper/2210.02074/) (2022)
- [Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies](https://mlsanity.com/paper/2203.13716/) (2022)
- [PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies](https://mlsanity.com/paper/2303.10704/) (2023)
- [Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detection](https://mlsanity.com/paper/2303.05116/) (2023)
- [Reconstruction Error-based Anomaly Detection with Few Outlying Examples](https://mlsanity.com/paper/2305.10464/) (2023)
- [Detecting and Learning the Unknown in Semantic Segmentation](https://mlsanity.com/paper/2202.08700/) (2022)
- [Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies](https://mlsanity.com/paper/2405.05886/) (2024)
- [Deep Visual Anomaly detection with Negative Learning](https://mlsanity.com/paper/2105.11058/) (2021)
- [Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data](https://mlsanity.com/paper/2403.16270/) (2024)
- [Anomaly Discovery in Semantic Segmentation via Distillation Comparison Networks](https://mlsanity.com/paper/2112.09908/) (2021)
- [Synthetic Pseudo Anomalies for Unsupervised Video Anomaly Detection: A Simple yet Efficient Framework based on Masked Autoencoder](https://mlsanity.com/paper/2303.05112/) (2023)

## Abstract (arXiv)

Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of training data. A less researched type of techniques concerns generation of only a single type of input. This is useful for applications such as constraint handling, noise reduction and anomaly detection. In this paper we present a technique to limit the generative capability of the network using negative learning. The proposed method searches the solution in the gradient direction for the desired input and in the opposite direction for the undesired input. One of the application can be anomaly detection where the undesired inputs are the anomalous data. In the results section we demonstrate the features of the algorithm using MNIST handwritten digit dataset and latter apply the technique to a real-world obstacle detection problem. The results clearly show that the proposed learning technique can significantly improve the performance for anomaly detection.