# An Effective Baseline for Robustness to Distributional Shift

arXiv: https://arxiv.org/abs/2105.07107 · HTML: https://mlsanity.com/paper/2105.07107/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 15 May 2021.

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Stochastic Gradient Descent as Approximate Bayesian Inference](https://mlsanity.com/paper/1704.04289/) (2017)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Practical Deep Learning with Bayesian Principles](https://mlsanity.com/paper/1906.02506/) (2019)
- [Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers](https://mlsanity.com/paper/1809.03576/) (2018)
- [Out-of-distribution Detection in Classifiers via Generation](https://mlsanity.com/paper/1910.04241/) (2019)

## Built on by (most cited first, 25 of 25)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2203.02194/) (2022)
- [Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey](https://mlsanity.com/paper/2407.21794/) (2024)
- [Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities](https://mlsanity.com/paper/2206.09880/) (2022)
- [Open-Set Semi-Supervised Object Detection](https://mlsanity.com/paper/2208.13722/) (2022)
- [The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition](https://mlsanity.com/paper/2302.04002/) (2023)
- [Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness](https://mlsanity.com/paper/2310.02832/) (2023)
- [Plugin estimators for selective classification with out-of-distribution detection](https://mlsanity.com/paper/2301.12386/) (2023)
- [Out-of-Distribution Detection Methods Answer the Wrong Questions](https://mlsanity.com/paper/2507.01831/) (2025)
- [Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing](https://mlsanity.com/paper/2304.04906/) (2023)
- [Out of Distribution Detection on ImageNet-O](https://mlsanity.com/paper/2201.09352/) (2022)
- [Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approach](https://mlsanity.com/paper/2410.21346/) (2024)
- [Weak-to-Strong Generalization under Distribution Shifts](https://mlsanity.com/paper/2510.21332/) (2025)
- [CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing](https://mlsanity.com/paper/2304.13616/) (2023)
- [Characterizing Data Point Vulnerability via Average-Case Robustness](https://mlsanity.com/paper/2307.13885/) (2023)
- [Dishonesty in Helpful and Harmless Alignment](https://mlsanity.com/paper/2406.01931/) (2024)
- [On effects of Knowledge Distillation on Transfer Learning](https://mlsanity.com/paper/2210.09668/) (2022)
- [Text Classification using Graph Convolutional Networks: A Comprehensive Survey](https://mlsanity.com/paper/2410.09399/) (2024)
- [Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation](https://mlsanity.com/paper/2512.08216/) (2025)
- [Low-Entropy Latent Variables Hurt Out-of-Distribution Performance](https://mlsanity.com/paper/2305.12238/) (2023)
- [Robust Uncertainty Estimation for Classification of Maritime Objects](https://mlsanity.com/paper/2307.01325/) (2023)
- [Incremental Object-Based Novelty Detection with Feedback Loop](https://mlsanity.com/paper/2311.09004/) (2023)
- [Revisiting Energy-Based Model for Out-of-Distribution Detection](https://mlsanity.com/paper/2412.03058/) (2024)
- [XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge](https://mlsanity.com/paper/2506.22726/) (2025)
- [Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning](https://mlsanity.com/paper/2509.17034/) (2025)

## Abstract (arXiv)

Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep learning systems. While simple to state, this has been a particularly challenging problem in deep learning, where models often end up making overconfident predictions in such situations. In this work we present a simple, but highly effective approach to deal with out-of-distribution detection that uses the principle of abstention: when encountering a sample from an unseen class, the desired behavior is to abstain from predicting. Our approach uses a network with an extra abstention class and is trained on a dataset that is augmented with an uncurated set that consists of a large number of out-of-distribution (OoD) samples that are assigned the label of the abstention class; the model is then trained to learn an effective discriminator between in and out-of-distribution samples. We compare this relatively simple approach against a wide variety of more complex methods that have been proposed both for out-of-distribution detection as well as uncertainty modeling in deep learning, and empirically demonstrate its effectiveness on a wide variety of of benchmarks and deep architectures for image recognition and text classification, often outperforming existing approaches by significant margins. Given the simplicity and effectiveness of this method, we propose that this approach be used as a new additional baseline for future work in this domain.