# Denoising Autoencoders for Overgeneralization in Neural Networks

arXiv: https://arxiv.org/abs/1709.04762 · HTML: https://mlsanity.com/paper/1709.04762/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2017.

## Built on by (most cited first, 5 of 5)

- [Collective Decision of One-vs-Rest Networks for Open Set Recognition](https://mlsanity.com/paper/2103.10230/) (2021)
- [Teacher-Explorer-Student Learning: A Novel Learning Method for Open Set Recognition](https://mlsanity.com/paper/2103.12871/) (2021)
- [Synthetic Unknown Class Learning for Learning Unknowns](https://mlsanity.com/paper/2111.08062/) (2021)
- [Scrutinizing Shipment Records To Thwart Illegal Timber Trade](https://mlsanity.com/paper/2208.00493/) (2022)
- [Detecting Anomalies Through Contrast in Heterogeneous Data](https://mlsanity.com/paper/2104.01156/) (2021)

## Abstract (arXiv)

Despite the recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem of overgeneralization, due to their partitioning of the full input space into the fixed set of target classes used during training. Thus it is possible for novel inputs belonging to categories unknown during training or even completely unrecognizable to humans to fool the system into classifying them as one of the known classes, even with a high degree of confidence. Solving this problem may help improve the security of such systems in critical applications, and may further lead to applications in the context of open set recognition and 1-class recognition. This paper presents a novel way to compute a confidence score using denoising autoencoders and shows that such confidence score can correctly identify the regions of the input space close to the training distribution by approximately identifying its local maxima.