# Generatively Augmented Neural Network Watchdog for Image Classification Networks

arXiv: https://arxiv.org/abs/2109.06168 · HTML: https://mlsanity.com/paper/2109.06168/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 70 references that are in the map.
- First posted on arXiv 7 Sep 2021.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Challenges in Deploying Machine Learning: a Survey of Case Studies](https://mlsanity.com/paper/2011.09926/) (2020)
- [Deep Learning for Financial Applications : A Survey](https://mlsanity.com/paper/2002.05786/) (2020)
- [Medical image denoising using convolutional denoising autoencoders](https://mlsanity.com/paper/1608.04667/) (2016)
- [Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes](https://mlsanity.com/paper/1609.00866/) (2016)
- [Improving Deep Learning using Generic Data Augmentation](https://mlsanity.com/paper/1708.06020/) (2017)
- [Data Augmentation in Emotion Classification Using Generative Adversarial Networks](https://mlsanity.com/paper/1711.00648/) (2017)
- [Autoencoder Watchdog Outlier Detection for Classifiers](https://mlsanity.com/paper/2010.12754/) (2020)
- [Symbiotic Hybrid Neural Network Watchdog For Outlier Detection](https://mlsanity.com/paper/2103.00582/) (2021)
- [Toward Metrics for Differentiating Out-of-Distribution Sets](https://mlsanity.com/paper/1910.08650/) (2019)
- [Classification of Common Waveforms Including a Watchdog for Unknown Signals](https://mlsanity.com/paper/2108.07339/) (2021)
- [Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection](https://mlsanity.com/paper/2108.09375/) (2021)

## Abstract (arXiv)

The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.