mlsanityData to 7 Oct 2026

Generatively Augmented Neural Network Watchdog for Image Classification Networks

arXiv 2109.06168 ↗First posted 7 Sep 2021cs.CV cs.LG eess.IVcited by 0

Not on the map. Why?

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.

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

Builds on

21 of 70 references.

References · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016Least Squares Generative Adversarial Networkscited by 1,000
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  5. 2017Generative Adversarial Networks: An Overviewcited by 588
  6. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  7. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  8. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  9. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  10. 2016Unrolled Generative Adversarial Networkscited by 208
  11. 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 151
  12. 2020Deep Learning for Financial Applications : A Surveycited by 90
9 more
  1. 2016Medical image denoising using convolutional denoising autoencoderscited by 76
  2. 2016Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenescited by 50
  3. 2017Improving Deep Learning using Generic Data Augmentationcited by 36
  4. 2017Data Augmentation in Emotion Classification Using Generative Adversarial Networkscited by 19
  5. 2020Autoencoder Watchdog Outlier Detection for Classifierscited by 5
  6. 2021Symbiotic Hybrid Neural Network Watchdog For Outlier Detectioncited by 2
  7. 2019Toward Metrics for Differentiating Out-of-Distribution Setscited by 1
  8. 2021Classification of Common Waveforms Including a Watchdog for Unknown Signalscited by 1
  9. 2021Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detectioncited by 1

Built on by

Not cited yet.