# Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection

arXiv: https://arxiv.org/abs/2203.02194 · HTML: https://mlsanity.com/paper/2203.02194/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 4 Mar 2022.

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

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [Classification-Reconstruction Learning for Open-Set Recognition](https://mlsanity.com/paper/1812.04246/) (2018)
- [Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers](https://mlsanity.com/paper/1809.03576/) (2018)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness](https://mlsanity.com/paper/1905.13472/) (2019)
- [Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance](https://mlsanity.com/paper/1812.02765/) (2018)
- [Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge](https://mlsanity.com/paper/1709.09121/) (2017)
- [An Effective Baseline for Robustness to Distributional Shift](https://mlsanity.com/paper/2105.07107/) (2021)
- [Robust, Deep and Inductive Anomaly Detection](https://mlsanity.com/paper/1704.06743/) (2017)
- [Out-of-Distribution Detection using Multiple Semantic Label Representations](https://mlsanity.com/paper/1808.06664/) (2018)
- [Web-Scale Training for Face Identification](https://mlsanity.com/paper/1406.5266/) (2014)
- [Roundtrip: A Deep Generative Neural Density Estimator](https://mlsanity.com/paper/2004.09017/) (2020)

## Built on by (most cited first, 30 of 59)

- [OpenOOD: Benchmarking Generalized Out-of-Distribution Detection](https://mlsanity.com/paper/2210.07242/) (2022)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization](https://mlsanity.com/paper/2407.09359/) (2024)
- [Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection](https://mlsanity.com/paper/2406.00806/) (2024)
- [MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities](https://mlsanity.com/paper/2405.17419/) (2024)
- [Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances](https://mlsanity.com/paper/2409.11884/) (2024)
- [ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.17888/) (2024)
- [Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data](https://mlsanity.com/paper/2412.06284/) (2024)
- [MirrorCheck: Efficient Adversarial Defense for Vision-Language Models](https://mlsanity.com/paper/2406.09250/) (2024)
- [ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference](https://mlsanity.com/paper/2211.11435/) (2022)
- [Detecting Out-Of-Distribution Earth Observation Images with Diffusion Models](https://mlsanity.com/paper/2404.12667/) (2024)
- [Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models](https://mlsanity.com/paper/2410.08611/) (2024)
- [Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos](https://mlsanity.com/paper/2311.00469/) (2023)
- [Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection](https://mlsanity.com/paper/2409.09953/) (2024)
- [Enabling Uncertainty Estimation in Iterative Neural Networks](https://mlsanity.com/paper/2403.16732/) (2024)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2307.15252/) (2023)
- [Autoencoders for Anomaly Detection are Unreliable](https://mlsanity.com/paper/2501.13864/) (2025)
- [Pedestrian Attribute Recognition as Label-balanced Multi-label Learning](https://mlsanity.com/paper/2405.04858/) (2024)
- [Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection](https://mlsanity.com/paper/2412.15668/) (2024)
- [Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection](https://mlsanity.com/paper/2506.17633/) (2025)
- [Out-of-Distribution Detection for Monocular Depth Estimation](https://mlsanity.com/paper/2308.06072/) (2023)
- [What do we learn? Debunking the Myth of Unsupervised Outlier Detection](https://mlsanity.com/paper/2206.03698/) (2022)
- [Unsupervised Recognition of Unknown Objects for Open-World Object Detection](https://mlsanity.com/paper/2308.16527/) (2023)
- [Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization](https://mlsanity.com/paper/2506.10233/) (2025)
- [Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection](https://mlsanity.com/paper/2310.18104/) (2023)
- [Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection](https://mlsanity.com/paper/2411.10701/) (2024)
- [Digital Twin-based Out-of-Distribution Detection in Autonomous Vessels](https://mlsanity.com/paper/2504.19816/) (2025)
- [EquiReg: Equivariance Regularized Diffusion for Inverse Problems](https://mlsanity.com/paper/2505.22973/) (2025)
- [FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection](https://mlsanity.com/paper/2507.04511/) (2025)

## Abstract (arXiv)

In some scenarios, classifier requires detecting out-of-distribution samples far from its training data. With desirable characteristics, reconstruction autoencoder-based methods deal with this problem by using input reconstruction error as a metric of novelty vs. normality. We formulate the essence of such approach as a quadruplet domain translation with an intrinsic bias to only query for a proxy of conditional data uncertainty. Accordingly, an improvement direction is formalized as maximumly compressing the autoencoder's latent space while ensuring its reconstructive power for acting as a described domain translator. From it, strategies are introduced including semantic reconstruction, data certainty decomposition and normalized L2 distance to substantially improve original methods, which together establish state-of-the-art performance on various benchmarks, e.g., the FPR@95%TPR of CIFAR-100 vs. TinyImagenet-crop on Wide-ResNet is 0.2%. Importantly, our method works without any additional data, hard-to-implement structure, time-consuming pipeline, and even harming the classification accuracy of known classes.