# Building robust classifiers through generation of confident out of distribution examples

arXiv: https://arxiv.org/abs/1812.00239 · HTML: https://mlsanity.com/paper/1812.00239/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2018.

## Built on by (most cited first, 20 of 20)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Provable Guarantees for Understanding Out-of-distribution Detection](https://mlsanity.com/paper/2112.00787/) (2021)
- [SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection](https://mlsanity.com/paper/2208.13930/) (2022)
- [Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources](https://mlsanity.com/paper/2311.03236/) (2023)
- [DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models](https://mlsanity.com/paper/2308.07687/) (2023)
- [Out-of-Distribution Detection with Semantic Mismatch under Masking](https://mlsanity.com/paper/2208.00446/) (2022)
- [Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection](https://mlsanity.com/paper/2303.10449/) (2023)
- [On Out-of-distribution Detection with Energy-based Models](https://mlsanity.com/paper/2107.08785/) (2021)
- [UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs](https://mlsanity.com/paper/2201.13279/) (2022)
- [Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders](https://mlsanity.com/paper/2105.02965/) (2021)
- [Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection](https://mlsanity.com/paper/2412.15668/) (2024)
- [Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection](https://mlsanity.com/paper/2211.11255/) (2022)
- [Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis](https://mlsanity.com/paper/2407.15763/) (2024)
- [Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity](https://mlsanity.com/paper/2409.05466/) (2024)
- [OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary](https://mlsanity.com/paper/2110.15273/) (2021)
- [FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection](https://mlsanity.com/paper/2111.15487/) (2021)
- [Silver Linings in the Shadows: Harnessing Membership Inference for Machine Unlearning](https://mlsanity.com/paper/2407.00866/) (2024)
- [Master's Thesis: Out-of-distribution Detection with Energy-based Models](https://mlsanity.com/paper/2302.12002/) (2023)
- [Revisiting Energy-Based Model for Out-of-Distribution Detection](https://mlsanity.com/paper/2412.03058/) (2024)
- [Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation](https://mlsanity.com/paper/2509.20587/) (2025)

## Abstract (arXiv)

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recently, there has been work on building classifiers that are robust to out of distribution samples by adding a regularization term that maximizes the entropy of the classifier output on out of distribution data. To approximate out of distribution samples (which are not known apriori), a GAN was used for generation of samples at the edges of the training distribution. In this paper, we introduce an alternative GAN based approach for building a robust classifier, where the idea is to use the GAN to explicitly generate out of distribution samples that the classifier is confident on (low entropy), and have the classifier maximize the entropy for these samples. We showcase the effectiveness of our approach relative to state-of-the-art on hand-written characters as well as on a variety of natural image datasets.