# Synthetic Unknown Class Learning for Learning Unknowns

arXiv: https://arxiv.org/abs/2111.08062 · HTML: https://mlsanity.com/paper/2111.08062/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 15 Nov 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Robustness via curvature regularization, and vice versa](https://mlsanity.com/paper/1811.09716/) (2018)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Generalization in Deep Learning](https://mlsanity.com/paper/1710.05468/) (2017)
- [Classification-Reconstruction Learning for Open-Set Recognition](https://mlsanity.com/paper/1812.04246/) (2018)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [DOC: Deep Open Classification of Text Documents](https://mlsanity.com/paper/1709.08716/) (2017)
- [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020)
- [Identifying Unknown Instances for Autonomous Driving](https://mlsanity.com/paper/1910.11296/) (2019)
- [Collective Decision of One-vs-Rest Networks for Open Set Recognition](https://mlsanity.com/paper/2103.10230/) (2021)
- [Denoising Autoencoders for Overgeneralization in Neural Networks](https://mlsanity.com/paper/1709.04762/) (2017)
- [Teacher-Explorer-Student Learning: A Novel Learning Method for Open Set Recognition](https://mlsanity.com/paper/2103.12871/) (2021)

## Built on by (most cited first, 1 of 1)

- [Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery](https://mlsanity.com/paper/2603.13858/) (2026)

## Abstract (arXiv)

This paper addresses the open set recognition (OSR) problem, where the goal is to correctly classify samples of known classes while detecting unknown samples to reject. In the OSR problem, "unknown" is assumed to have infinite possibilities because we have no knowledge about unknowns until they emerge. Intuitively, the more an OSR system explores the possibilities of unknowns, the more likely it is to detect unknowns. Thus, this paper proposes a novel synthetic unknown class learning method that generates unknown-like samples while maintaining diversity between the generated samples and learns these samples. In addition to this unknown sample generation process, knowledge distillation is introduced to provide room for learning synthetic unknowns. By learning the unknown-like samples and known samples in an alternating manner, the proposed method can not only experience diverse synthetic unknowns but also reduce overgeneralization with respect to known classes. Experiments on several benchmark datasets show that the proposed method significantly outperforms other state-of-the-art approaches. It is also shown that realistic unknown digits can be generated and learned via the proposed method after training on the MNIST dataset.